{"name":"Open AI models: parameters, active parameters and memory","id":"models","version":"2026-10-19","dateModified":"2026-10-19","url":"https://mlx.app/data#models","license":"https://creativecommons.org/licenses/by/4.0/","attribution":"MLX Network, https://mlx.app/data","description":"Every open-weight language model on mlx.app/compare: total and active parameters, architecture (dense or mixture of experts), context length, licence, release date, precision and weight size, read from each model's official Hugging Face card, config.json and file listing.","method":"https://mlx.app/compare#cp-how","sources":[{"text":"Official model cards and config.json files on Hugging Face, linked per row","href":"https://huggingface.co/"}],"columns":[{"name":"model","type":"string","description":"Identifier, as in mlx.app/run/<model>"},{"name":"name","type":"string","description":"Model name"},{"name":"maker","type":"string","description":"Who released it"},{"name":"hf_repo","type":"string","description":"Official Hugging Face repository"},{"name":"params_b","type":"number","description":"Total parameters, billions (model card)"},{"name":"active_params_b","type":"number","description":"Parameters read per generated token, billions (equals params_b for dense models, except a looped model, which reads its shared block once per loop: at its default loop count)"},{"name":"architecture","type":"string","description":"dense or moe"},{"name":"context_tokens","type":"number","description":"Maximum context, tokens (config.json)"},{"name":"license","type":"string","description":"Licence named on the card"},{"name":"released","type":"string","description":"Release date (YYYY-MM-DD; the repository's creation date where the card gives none)"},{"name":"modality","type":"string","description":"Inputs: text, or text+image"},{"name":"precision","type":"string","description":"Precision of the official weights"},{"name":"repo_weights_gb","type":"number","description":"Size of the official weight files, decimal GB"},{"name":"native_gb","type":"number","description":"Weights in the model's native low-bit format, GB (only models released that way)"},{"name":"native_bits","type":"number","description":"Bits per weight of that native format"},{"name":"offload_gb","type":"number","description":"Lookup tables a runtime can leave on disk, GB (not counted in memory estimates)"},{"name":"mlx_build","type":"string","description":"A community MLX build on Hugging Face, where one exists"},{"name":"page","type":"string","description":"Page on mlx.app with the memory it needs and every Mac that runs it"},{"name":"sources","type":"string","description":"Pages the figures were read from (list)"}],"rows":[{"model":"deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","maker":"DeepSeek","hf_repo":"deepseek-ai/DeepSeek-V4-Flash-0731","params_b":284,"active_params_b":13,"architecture":"moe","context_tokens":1048576,"license":"MIT","released":"2026-07-31","modality":"text","precision":"FP4 (MoE experts) + FP8 mixed","repo_weights_gb":166.89,"native_gb":null,"native_bits":null,"offload_gb":null,"mlx_build":"mlx-community/DeepSeek-V4-Flash-4bit","page":"https://mlx.app/run/deepseek-v4-flash-0731","sources":["https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash-0731","https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro"]},{"model":"deepseek-v4.1-flash-1017","name":"DeepSeek V4.1 Flash 1017","maker":"DeepSeek","hf_repo":"deepseek-ai/DeepSeek-V4.1-Flash-1017","params_b":552,"active_params_b":16,"architecture":"moe","context_tokens":1048576,"license":"MIT","released":"2026-10-17","modality":"text+image","precision":"FP4 routed experts + FP8 dense (config quant fp8, expert_dtype fp4); Engram tables FP8 (E4M3)","repo_weights_gb":510.3,"native_gb":null,"native_bits":null,"offload_gb":202.76,"mlx_build":"mlx-community/DeepSeek-V4.1-Flash-1017-oQ4e-mtp","page":"https://mlx.app/run/deepseek-v4.1-flash-1017","sources":["https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017","https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash","https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017/blob/main/config.json","https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017/blob/main/model.safetensors.index.json","https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017/blob/main/inference/README.md"]},{"model":"deepseek-v4-pro-0813","name":"DeepSeek V4 Pro 0813","maker":"DeepSeek","hf_repo":"deepseek-ai/DeepSeek-V4-Pro-0813","params_b":1600,"active_params_b":49,"architecture":"moe","context_tokens":1048576,"license":"MIT","released":"2026-08-13","modality":"text","precision":"FP4 (MoE experts) + FP8 mixed","repo_weights_gb":892.74,"native_gb":null,"native_bits":null,"offload_gb":null,"mlx_build":"mlx-community/DeepSeek-V4-Pro-4bit","page":"https://mlx.app/run/deepseek-v4-pro-0813","sources":["https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813","https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro"]},{"model":"gemma-4-e2b","name":"Gemma 4 E2B","maker":"Google DeepMind","hf_repo":"google/gemma-4-E2B-it","params_b":5.1,"active_params_b":2.3,"architecture":"dense","context_tokens":131072,"license":"Apache-2.0","released":"2026-03-02","modality":"text+image+audio","precision":"BF16","repo_weights_gb":10.25,"native_gb":null,"native_bits":null,"offload_gb":null,"mlx_build":"mlx-community/gemma-4-e2b-it-4bit","page":"https://mlx.app/run/gemma-4-e2b","sources":["https://huggingface.co/google/gemma-4-E2B-it","https://huggingface.co/google/gemma-4-E2B-it/blob/main/config.json"]},{"model":"gemma-4-e4b","name":"Gemma 4 E4B","maker":"Google DeepMind","hf_repo":"google/gemma-4-E4B-it","params_b":8,"active_params_b":4.5,"architecture":"dense","context_tokens":131072,"license":"Apache-2.0","released":"2026-03-02","modality":"text+image+audio","precision":"BF16","repo_weights_gb":15.99,"native_gb":null,"native_bits":null,"offload_gb":null,"mlx_build":"mlx-community/gemma-4-e4b-it-4bit","page":"https://mlx.app/run/gemma-4-e4b","sources":["https://huggingface.co/google/gemma-4-E4B-it","https://huggingface.co/google/gemma-4-E4B-it/blob/main/config.json"]},{"model":"gemma-4-12b","name":"Gemma 4 12B Unified","maker":"Google DeepMind","hf_repo":"google/gemma-4-12B-it","params_b":11.95,"active_params_b":11.95,"architecture":"dense","context_tokens":262144,"license":"Apache-2.0","released":"2026-05-23","modality":"text+image+audio","precision":"BF16","repo_weights_gb":23.92,"native_gb":null,"native_bits":null,"offload_gb":null,"mlx_build":"mlx-community/gemma-4-12B-it-4bit","page":"https://mlx.app/run/gemma-4-12b","sources":["https://huggingface.co/google/gemma-4-12B-it","https://huggingface.co/google/gemma-4-12B-it/blob/main/config.json"]},{"model":"gemma-4-26b-a4b","name":"Gemma 4 26B A4B","maker":"Google DeepMind","hf_repo":"google/gemma-4-26B-A4B-it","params_b":25.2,"active_params_b":3.8,"architecture":"moe","context_tokens":262144,"license":"Apache-2.0","released":"2026-03-11","modality":"text+image","precision":"BF16","repo_weights_gb":51.61,"native_gb":null,"native_bits":null,"offload_gb":null,"mlx_build":"mlx-community/gemma-4-26b-a4b-it-4bit","page":"https://mlx.app/run/gemma-4-26b-a4b","sources":["https://huggingface.co/google/gemma-4-26B-A4B-it","https://huggingface.co/google/gemma-4-26B-A4B-it/blob/main/config.json"]},{"model":"gemma-4-31b","name":"Gemma 4 31B","maker":"Google DeepMind","hf_repo":"google/gemma-4-31B-it","params_b":30.7,"active_params_b":30.7,"architecture":"dense","context_tokens":262144,"license":"Apache-2.0","released":"2026-03-11","modality":"text+image","precision":"BF16","repo_weights_gb":62.55,"native_gb":null,"native_bits":null,"offload_gb":null,"mlx_build":"mlx-community/gemma-4-31b-it-4bit","page":"https://mlx.app/run/gemma-4-31b","sources":["https://huggingface.co/google/gemma-4-31B-it","https://huggingface.co/google/gemma-4-31B-it/blob/main/config.json"]},{"model":"smollm3-3b","name":"SmolLM3 3B","maker":"Hugging Face","hf_repo":"HuggingFaceTB/SmolLM3-3B","params_b":3,"active_params_b":3,"architecture":"dense","context_tokens":65536,"license":"Apache-2.0","released":"2025-07-08","modality":"text","precision":"BF16","repo_weights_gb":6.15,"native_gb":null,"native_bits":null,"offload_gb":null,"mlx_build":"mlx-community/SmolLM3-3B-4bit","page":"https://mlx.app/run/smollm3-3b","sources":["https://huggingface.co/HuggingFaceTB/SmolLM3-3B","https://huggingface.co/HuggingFaceTB/SmolLM3-3B/blob/main/config.json"]},{"model":"granite-4.2-3b","name":"Granite 4.2 3B","maker":"IBM","hf_repo":"ibm-granite/granite-4.2-3b","params_b":3,"active_params_b":3,"architecture":"dense","context_tokens":131072,"license":"Apache-2.0","released":"2026-08-25","modality":"text","precision":"BF16","repo_weights_gb":7.32,"native_gb":null,"native_bits":null,"offload_gb":null,"mlx_build":null,"page":"https://mlx.app/run/granite-4.2-3b","sources":["https://huggingface.co/ibm-granite/granite-4.2-3b","https://huggingface.co/ibm-granite/granite-4.2-3b/blob/main/config.json"]},{"model":"granite-4.2-8b","name":"Granite 4.2 8B","maker":"IBM","hf_repo":"ibm-granite/granite-4.2-8b","params_b":8,"active_params_b":8,"architecture":"dense","context_tokens":131072,"license":"Apache-2.0","released":"2026-08-25","modality":"text","precision":"BF16","repo_weights_gb":17.58,"native_gb":null,"native_bits":null,"offload_gb":null,"mlx_build":null,"page":"https://mlx.app/run/granite-4.2-8b","sources":["https://huggingface.co/ibm-granite/granite-4.2-8b","https://huggingface.co/ibm-granite/granite-4.2-8b/blob/main/config.json"]},{"model":"granite-4.2-30b","name":"Granite 4.2 30B","maker":"IBM","hf_repo":"ibm-granite/granite-4.2-30b","params_b":30,"active_params_b":30,"architecture":"dense","context_tokens":131072,"license":"Apache-2.0","released":"2026-08-25","modality":"text","precision":"BF16","repo_weights_gb":58.55,"native_gb":null,"native_bits":null,"offload_gb":null,"mlx_build":null,"page":"https://mlx.app/run/granite-4.2-30b","sources":["https://huggingface.co/ibm-granite/granite-4.2-30b","https://huggingface.co/ibm-granite/granite-4.2-30b/blob/main/config.json"]},{"model":"ling-3.1-flash","name":"Ling 3.1 Flash","maker":"inclusionAI","hf_repo":"inclusionAI/Ling-3.1-flash","params_b":560,"active_params_b":25,"architecture":"moe","context_tokens":262144,"license":"MIT","released":"2026-10-13","modality":"text","precision":"FP8 (block-wise E4M3, 128x128; HF metadata: 570.63B F8_E4M3 + 1.49B BF16)","repo_weights_gb":573.78,"native_gb":null,"native_bits":null,"offload_gb":null,"mlx_build":null,"page":"https://mlx.app/run/ling-3.1-flash","sources":["https://huggingface.co/inclusionAI/Ling-3.1-flash","https://huggingface.co/inclusionAI/Ling-3.1-flash/blob/main/config.json","https://huggingface.co/api/models/inclusionAI/Ling-3.1-flash","https://huggingface.co/bartowski/Ling-3.1-flash-GGUF"]},{"model":"raon-1-mini-preview","name":"Raon-1 mini Preview","maker":"KRAFTON","hf_repo":"KRAFTON/Raon-1-mini-preview","params_b":28.8,"active_params_b":4.3,"architecture":"moe","context_tokens":262144,"license":"Apache-2.0","released":"2026-10-21","modality":"text","precision":"MXFP8 (HF metadata: 25.67B F8_E4M3 + 3.11B BF16); official NVFP4, MLX and GGUF repos","repo_weights_gb":32.7,"native_gb":null,"native_bits":null,"offload_gb":null,"mlx_build":"KRAFTON/Raon-1-mini-preview-mlx","page":"https://mlx.app/run/raon-1-mini-preview","sources":["https://huggingface.co/KRAFTON/Raon-1-mini-preview","https://huggingface.co/api/models/KRAFTON/Raon-1-mini-preview","https://huggingface.co/KRAFTON/Raon-1-mini-preview-mlx","https://huggingface.co/KRAFTON/Raon-1-mini-preview-gguf"]},{"model":"lfm2.5-2.6b","name":"LFM2.5 2.6B","maker":"Liquid AI","hf_repo":"LiquidAI/LFM2.5-2.6B","params_b":2.69,"active_params_b":2.69,"architecture":"dense","context_tokens":131072,"license":"LFM Open License v1.0 (lfm1.0)","released":"2026-07-28","modality":"text","precision":"BF16","repo_weights_gb":5.39,"native_gb":null,"native_bits":null,"offload_gb":null,"mlx_build":"mlx-community/LFM2.5-2.6B-4bit","page":"https://mlx.app/run/lfm2.5-2.6b","sources":["https://huggingface.co/LiquidAI/LFM2.5-2.6B","https://huggingface.co/LiquidAI/LFM2.5-2.6B/blob/main/config.json"]},{"model":"lfm2.5-24b-a2b","name":"LFM2.5 24B A2B","maker":"Liquid AI","hf_repo":"LiquidAI/LFM2.5-24B-A2B","params_b":24,"active_params_b":2,"architecture":"moe","context_tokens":131072,"license":"LFM Open License v1.0 (lfm1.0)","released":"2026-10-12","modality":"text","precision":"BF16 (official FP8 repo)","repo_weights_gb":47.94,"native_gb":null,"native_bits":null,"offload_gb":null,"mlx_build":"mlx-community/LFM2.5-24B-A2B-OptiQ-4bit","page":"https://mlx.app/run/lfm2.5-24b-a2b","sources":["https://huggingface.co/LiquidAI/LFM2.5-24B-A2B","https://huggingface.co/LiquidAI/LFM2.5-24B-A2B/blob/main/config.json"]},{"model":"llama-3.2-1b","name":"Llama 3.2 1B Instruct","maker":"Meta","hf_repo":"meta-llama/Llama-3.2-1B-Instruct","params_b":1.23,"active_params_b":1.23,"architecture":"dense","context_tokens":131072,"license":"Llama 3.2 Community License","released":"2024-09-25","modality":"text","precision":"BF16","repo_weights_gb":2.47,"native_gb":null,"native_bits":null,"offload_gb":null,"mlx_build":"mlx-community/Llama-3.2-1B-Instruct-4bit","page":"https://mlx.app/run/llama-3.2-1b","sources":["https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct","https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct/blob/main/config.json","https://huggingface.co/mlx-community/Llama-3.2-1B-Instruct-4bit/blob/main/config.json"]},{"model":"llama-3.2-3b","name":"Llama 3.2 3B Instruct","maker":"Meta","hf_repo":"meta-llama/Llama-3.2-3B-Instruct","params_b":3.21,"active_params_b":3.21,"architecture":"dense","context_tokens":131072,"license":"Llama 3.2 Community License","released":"2024-09-25","modality":"text","precision":"BF16","repo_weights_gb":6.43,"native_gb":null,"native_bits":null,"offload_gb":null,"mlx_build":"mlx-community/Llama-3.2-3B-Instruct-4bit","page":"https://mlx.app/run/llama-3.2-3b","sources":["https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct","https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct/blob/main/config.json","https://huggingface.co/mlx-community/Llama-3.2-3B-Instruct-4bit/blob/main/config.json"]},{"model":"llama-3.1-8b","name":"Llama 3.1 8B Instruct","maker":"Meta","hf_repo":"meta-llama/Llama-3.1-8B-Instruct","params_b":8,"active_params_b":8,"architecture":"dense","context_tokens":131072,"license":"Llama 3.1 Community License","released":"2024-07-23","modality":"text","precision":"BF16","repo_weights_gb":16.06,"native_gb":null,"native_bits":null,"offload_gb":null,"mlx_build":"mlx-community/Llama-3.1-8B-Instruct-4bit","page":"https://mlx.app/run/llama-3.1-8b","sources":["https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct","https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct/blob/main/config.json","https://huggingface.co/mlx-community/Llama-3.1-8B-Instruct-4bit/blob/main/config.json"]},{"model":"llama-3.3-70b","name":"Llama 3.3 70B Instruct","maker":"Meta","hf_repo":"meta-llama/Llama-3.3-70B-Instruct","params_b":70,"active_params_b":70,"architecture":"dense","context_tokens":131072,"license":"Llama 3.3 Community License","released":"2024-12-06","modality":"text","precision":"BF16","repo_weights_gb":141.11,"native_gb":null,"native_bits":null,"offload_gb":null,"mlx_build":"mlx-community/Llama-3.3-70B-Instruct-4bit","page":"https://mlx.app/run/llama-3.3-70b","sources":["https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct","https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct/blob/main/config.json","https://huggingface.co/mlx-community/Llama-3.3-70B-Instruct-4bit/blob/main/config.json"]},{"model":"llama-4-scout","name":"Llama 4 Scout 17B-16E Instruct","maker":"Meta","hf_repo":"meta-llama/Llama-4-Scout-17B-16E-Instruct","params_b":109,"active_params_b":17,"architecture":"moe","context_tokens":10485760,"license":"Llama 4 Community License","released":"2025-04-05","modality":"text+image","precision":"BF16","repo_weights_gb":217.28,"native_gb":null,"native_bits":null,"offload_gb":null,"mlx_build":"mlx-community/Llama-4-Scout-17B-16E-Instruct-4bit","page":"https://mlx.app/run/llama-4-scout","sources":["https://huggingface.co/meta-llama/Llama-4-Scout-17B-16E-Instruct","https://huggingface.co/meta-llama/Llama-4-Scout-17B-16E-Instruct/blob/main/config.json","https://huggingface.co/mlx-community/Llama-4-Scout-17B-16E-Instruct-4bit/blob/main/config.json"]},{"model":"llama-4-maverick","name":"Llama 4 Maverick 17B-128E Instruct","maker":"Meta","hf_repo":"meta-llama/Llama-4-Maverick-17B-128E-Instruct","params_b":400,"active_params_b":17,"architecture":"moe","context_tokens":1048576,"license":"Llama 4 Community License","released":"2025-04-05","modality":"text+image","precision":"BF16","repo_weights_gb":803.17,"native_gb":null,"native_bits":null,"offload_gb":null,"mlx_build":"mlx-community/Llama-4-Maverick-17B-128E-Instruct-4bit","page":"https://mlx.app/run/llama-4-maverick","sources":["https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E-Instruct","https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E-Instruct/blob/main/config.json","https://huggingface.co/mlx-community/Llama-4-Maverick-17B-128E-Instruct-4bit/blob/main/config.json"]},{"model":"muse-glimmer-30b","name":"Muse Glimmer 30B","maker":"Meta (Meta Superintelligence Lab)","hf_repo":"meta-models/Muse-Glimmer-30B","params_b":29.6,"active_params_b":29.6,"architecture":"dense","context_tokens":131072,"license":"Apache-2.0","released":"2026-08","modality":"text+image","precision":"BF16","repo_weights_gb":59.55,"native_gb":null,"native_bits":null,"offload_gb":null,"mlx_build":"mlx-community/Muse-Glimmer-30B-4bit","page":"https://mlx.app/run/muse-glimmer-30b","sources":["https://huggingface.co/meta-models/Muse-Glimmer-30B","https://huggingface.co/meta-models/Muse-Glimmer-30B/blob/main/config.json"]},{"model":"muse-spark-open","name":"Muse Spark Open","maker":"Meta (Meta Superintelligence Labs)","hf_repo":"meta-models/Muse-Spark-Open-816B-A42B","params_b":816,"active_params_b":42,"architecture":"moe","context_tokens":1048576,"license":"Muse Model License (custom; 'Built with Muse Spark Open' attribution, revenue clause for model-as-a-service)","released":"2026-10-15","modality":"text+image+video+audio","precision":"BF16 (official NVFP4 repo also published)","repo_weights_gb":1644.33,"native_gb":null,"native_bits":null,"offload_gb":null,"mlx_build":"mlx-community/Muse-Spark-Open-816B-A42B-4bit","page":"https://mlx.app/run/muse-spark-open","sources":["https://huggingface.co/meta-models/Muse-Spark-Open-816B-A42B","https://huggingface.co/meta-models/Muse-Spark-Open-816B-A42B/blob/main/config.json","https://huggingface.co/mlx-community/Muse-Spark-Open-816B-A42B-4bit/blob/main/config.json"]},{"model":"phi-4-mini","name":"Phi-4 mini instruct","maker":"Microsoft","hf_repo":"microsoft/Phi-4-mini-instruct","params_b":3.8,"active_params_b":3.8,"architecture":"dense","context_tokens":131072,"license":"MIT","released":"2025-02","modality":"text","precision":"BF16","repo_weights_gb":7.67,"native_gb":null,"native_bits":null,"offload_gb":null,"mlx_build":"mlx-community/Phi-4-mini-instruct-4bit","page":"https://mlx.app/run/phi-4-mini","sources":["https://huggingface.co/microsoft/Phi-4-mini-instruct","https://huggingface.co/microsoft/Phi-4-mini-instruct/blob/main/config.json"]},{"model":"phi-4","name":"Phi-4 (14B)","maker":"Microsoft","hf_repo":"microsoft/phi-4","params_b":14,"active_params_b":14,"architecture":"dense","context_tokens":16384,"license":"MIT","released":"2024-12-12","modality":"text","precision":"BF16","repo_weights_gb":29.32,"native_gb":null,"native_bits":null,"offload_gb":null,"mlx_build":"mlx-community/phi-4-4bit","page":"https://mlx.app/run/phi-4","sources":["https://huggingface.co/microsoft/phi-4","https://huggingface.co/microsoft/phi-4/blob/main/config.json"]},{"model":"phi-4-reasoning-vision-15b","name":"Phi-4 Reasoning Vision 15B","maker":"Microsoft","hf_repo":"microsoft/Phi-4-reasoning-vision-15B","params_b":15,"active_params_b":15,"architecture":"dense","context_tokens":16384,"license":"MIT","released":"2026-03-04","modality":"text+image","precision":"BF16","repo_weights_gb":30.24,"native_gb":null,"native_bits":null,"offload_gb":null,"mlx_build":null,"page":"https://mlx.app/run/phi-4-reasoning-vision-15b","sources":["https://huggingface.co/microsoft/Phi-4-reasoning-vision-15B","https://huggingface.co/microsoft/Phi-4-reasoning-vision-15B/blob/main/config.json"]},{"model":"minimax-m2.7","name":"MiniMax M2.7","maker":"MiniMax","hf_repo":"MiniMaxAI/MiniMax-M2.7","params_b":230,"active_params_b":10,"architecture":"moe","context_tokens":204800,"license":"MiniMax M2.7 license (custom, 'other')","released":"2026-04-09","modality":"text","precision":"FP8 (config quant_method fp8)","repo_weights_gb":230.13,"native_gb":null,"native_bits":null,"offload_gb":null,"mlx_build":"mlx-community/MiniMax-M2.7-4bit","page":"https://mlx.app/run/minimax-m2.7","sources":["https://huggingface.co/MiniMaxAI/MiniMax-M2.7","https://huggingface.co/MiniMaxAI/MiniMax-M2.7/blob/main/config.json","https://huggingface.co/MiniMaxAI/MiniMax-M2","https://huggingface.co/MiniMaxAI/MiniMax-M2/blob/main/config.json"]},{"model":"minimax-m3","name":"MiniMax M3","maker":"MiniMax","hf_repo":"MiniMaxAI/MiniMax-M3","params_b":428,"active_params_b":23,"architecture":"moe","context_tokens":1048576,"license":"MiniMax Community License (custom)","released":"2026-06-02","modality":"text+image","precision":"BF16 (official MXFP8 repo exists)","repo_weights_gb":854.18,"native_gb":null,"native_bits":null,"offload_gb":null,"mlx_build":"mlx-community/MiniMax-M3-4bit","page":"https://mlx.app/run/minimax-m3","sources":["https://huggingface.co/MiniMaxAI/MiniMax-M3","https://huggingface.co/MiniMaxAI/MiniMax-M3/blob/main/config.json"]},{"model":"ministral-3-8b","name":"Ministral 3 8B","maker":"Mistral AI","hf_repo":"mistralai/Ministral-3-8B-Instruct-2512","params_b":8.9,"active_params_b":8.9,"architecture":"dense","context_tokens":262144,"license":"Apache-2.0","released":"2025-10-31","modality":"text+image","precision":"FP8 (card; BF16 repo also published)","repo_weights_gb":10.42,"native_gb":null,"native_bits":null,"offload_gb":null,"mlx_build":"mlx-community/Ministral-3-8B-Instruct-2512-4bit","page":"https://mlx.app/run/ministral-3-8b","sources":["https://huggingface.co/mistralai/Ministral-3-8B-Instruct-2512","https://huggingface.co/mistralai/Ministral-3-8B-Instruct-2512/blob/main/config.json"]},{"model":"devstral-small-2","name":"Devstral Small 2 (24B)","maker":"Mistral AI","hf_repo":"mistralai/Devstral-Small-2-24B-Instruct-2512","params_b":24,"active_params_b":24,"architecture":"dense","context_tokens":262144,"license":"Apache-2.0","released":"2025-11-28","modality":"text+image","precision":"FP8 (card)","repo_weights_gb":25.79,"native_gb":null,"native_bits":null,"offload_gb":null,"mlx_build":"mlx-community/Devstral-Small-2-24B-Instruct-2512-4bit","page":"https://mlx.app/run/devstral-small-2","sources":["https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512","https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512/blob/main/config.json"]},{"model":"magistral-small-2509","name":"Magistral Small 1.2 (2509)","maker":"Mistral AI","hf_repo":"mistralai/Magistral-Small-2509","params_b":24,"active_params_b":24,"architecture":"dense","context_tokens":131072,"license":"Apache-2.0","released":"2025-09-12","modality":"text+image","precision":"BF16","repo_weights_gb":48.02,"native_gb":null,"native_bits":null,"offload_gb":null,"mlx_build":null,"page":"https://mlx.app/run/magistral-small-2509","sources":["https://huggingface.co/mistralai/Magistral-Small-2509","https://huggingface.co/mistralai/Magistral-Small-2509/blob/main/config.json"]},{"model":"mistral-small-3.2","name":"Mistral Small 3.2 (24B)","maker":"Mistral AI","hf_repo":"mistralai/Mistral-Small-3.2-24B-Instruct-2506","params_b":24,"active_params_b":24,"architecture":"dense","context_tokens":131072,"license":"Apache-2.0","released":"2025-06-19","modality":"text+image","precision":"BF16","repo_weights_gb":48.02,"native_gb":null,"native_bits":null,"offload_gb":null,"mlx_build":"mlx-community/Mistral-Small-3.2-24B-Instruct-2506-4bit","page":"https://mlx.app/run/mistral-small-3.2","sources":["https://huggingface.co/mistralai/Mistral-Small-3.2-24B-Instruct-2506","https://huggingface.co/mistralai/Mistral-Small-3.2-24B-Instruct-2506/blob/main/config.json"]},{"model":"mistral-small-4","name":"Mistral Small 4 (119B)","maker":"Mistral AI","hf_repo":"mistralai/Mistral-Small-4-119B-2603","params_b":119,"active_params_b":6.5,"architecture":"moe","context_tokens":262144,"license":"Apache-2.0","released":"2026-01-23","modality":"text+image","precision":"FP8 (config quant_method fp8; vision tower and lm_head unquantized)","repo_weights_gb":120.92,"native_gb":null,"native_bits":null,"offload_gb":null,"mlx_build":"mlx-community/Mistral-Small-4-119B-2603-4bit","page":"https://mlx.app/run/mistral-small-4","sources":["https://huggingface.co/mistralai/Mistral-Small-4-119B-2603","https://huggingface.co/mistralai/Mistral-Small-4-119B-2603/blob/main/config.json"]},{"model":"devstral-2-123b","name":"Devstral 2 (123B)","maker":"Mistral AI","hf_repo":"mistralai/Devstral-2-123B-Instruct-2512","params_b":123,"active_params_b":123,"architecture":"dense","context_tokens":262144,"license":"Modified MIT","released":"2025-11-28","modality":"text","precision":"FP8 (card)","repo_weights_gb":128.25,"native_gb":null,"native_bits":null,"offload_gb":null,"mlx_build":"mlx-community/Devstral-2-123B-Instruct-2512-4bit","page":"https://mlx.app/run/devstral-2-123b","sources":["https://huggingface.co/mistralai/Devstral-2-123B-Instruct-2512","https://huggingface.co/mistralai/Devstral-2-123B-Instruct-2512/blob/main/config.json"]},{"model":"mistral-medium-3.5","name":"Mistral Medium 3.5 (128B)","maker":"Mistral AI","hf_repo":"mistralai/Mistral-Medium-3.5-128B","params_b":128,"active_params_b":128,"architecture":"dense","context_tokens":262144,"license":"Modified MIT (exceptions for companies with large revenue)","released":"2026-03-31","modality":"text+image","precision":"FP8 (config quant_method fp8)","repo_weights_gb":133.61,"native_gb":null,"native_bits":null,"offload_gb":null,"mlx_build":"mlx-community/Mistral-Medium-3.5-128B-4bit","page":"https://mlx.app/run/mistral-medium-3.5","sources":["https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","https://huggingface.co/mistralai/Mistral-Medium-3.5-128B/blob/main/config.json"]},{"model":"mistral-large-3","name":"Mistral Large 3 (675B)","maker":"Mistral AI","hf_repo":"mistralai/Mistral-Large-3-675B-Instruct-2512","params_b":675,"active_params_b":41,"architecture":"moe","context_tokens":262144,"license":"Apache-2.0","released":"2025-11-28","modality":"text+image","precision":"FP8 (card; BF16 and NVFP4 repos also published)","repo_weights_gb":681.5,"native_gb":null,"native_bits":null,"offload_gb":null,"mlx_build":"mlx-community/Mistral-Large-3-675B-Instruct-2512-mlx-4bit","page":"https://mlx.app/run/mistral-large-3","sources":["https://huggingface.co/mistralai/Mistral-Large-3-675B-Instruct-2512","https://huggingface.co/mistralai/Mistral-Large-3-675B-Instruct-2512/blob/main/config.json"]},{"model":"kimi-k2.6","name":"Kimi K2.6","maker":"Moonshot AI","hf_repo":"moonshotai/Kimi-K2.6","params_b":1000,"active_params_b":32,"architecture":"moe","context_tokens":262144,"license":"Modified MIT","released":"2026-04-14","modality":"text+image","precision":"INT4 native (QAT, group 32) for experts; BF16 rest","repo_weights_gb":595.18,"native_gb":595.18,"native_bits":4,"offload_gb":null,"mlx_build":"mlx-community/Kimi-K2.6-mlx-DQ3_K_M-q8","page":"https://mlx.app/run/kimi-k2.6","sources":["https://huggingface.co/moonshotai/Kimi-K2.6","https://huggingface.co/moonshotai/Kimi-K2.6/blob/main/config.json"]},{"model":"kimi-k2.7-code","name":"Kimi K2.7 Code","maker":"Moonshot AI","hf_repo":"moonshotai/Kimi-K2.7-Code","params_b":1000,"active_params_b":32,"architecture":"moe","context_tokens":262144,"license":"Modified MIT","released":"2026-06-11","modality":"text+image","precision":"INT4 native (QAT); BF16 rest","repo_weights_gb":595.18,"native_gb":595.18,"native_bits":4,"offload_gb":null,"mlx_build":"mlx-community/Kimi-K2.7-Code-4bit","page":"https://mlx.app/run/kimi-k2.7-code","sources":["https://huggingface.co/moonshotai/Kimi-K2.7-Code","https://huggingface.co/moonshotai/Kimi-K2.7-Code/blob/main/config.json"]},{"model":"kimi-k3","name":"Kimi K3","maker":"Moonshot AI","hf_repo":"moonshotai/Kimi-K3","params_b":2800,"active_params_b":104,"architecture":"moe","context_tokens":1048576,"license":"Kimi K3 License (custom)","released":"2026-06-13","modality":"text+image","precision":"MXFP4 weights / MXFP8 activations (quantization-aware training)","repo_weights_gb":1560.94,"native_gb":1560.94,"native_bits":4.25,"offload_gb":null,"mlx_build":"mlx-community/Kimi-K3-mlx-reap160-2bit","page":"https://mlx.app/run/kimi-k3","sources":["https://huggingface.co/moonshotai/Kimi-K3","https://huggingface.co/moonshotai/Kimi-K3/blob/main/config.json"]},{"model":"nemotron-3-nano-4b","name":"Nemotron 3 Nano 4B","maker":"NVIDIA","hf_repo":"nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16","params_b":3.97,"active_params_b":3.97,"architecture":"dense","context_tokens":262144,"license":"NVIDIA Nemotron Open Model License","released":"2026-03-16","modality":"text","precision":"BF16","repo_weights_gb":7.95,"native_gb":null,"native_bits":null,"offload_gb":null,"mlx_build":"mlx-community/NVIDIA-Nemotron-3-Nano-4B-4bit","page":"https://mlx.app/run/nemotron-3-nano-4b","sources":["https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16","https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16/blob/main/config.json"]},{"model":"nemotron-labs-dory-1.0-4b","name":"Nemotron-Labs Dory 1.0 4B","maker":"NVIDIA","hf_repo":"nvidia/NVIDIA-Nemotron-Labs-Dory1.0-4B-BF16","params_b":3.98,"active_params_b":5.81,"architecture":"dense","context_tokens":262144,"license":"OpenMDW-1.1","released":"2026-10-16","modality":"text","precision":"BF16; official MXFP8, NVFP4 and Q5_K_M GGUF repos","repo_weights_gb":7.95,"native_gb":null,"native_bits":null,"offload_gb":null,"mlx_build":"snsnc/NVIDIA-Nemotron-Labs-Dory1.0-4B-mlx-4bit","page":"https://mlx.app/run/nemotron-labs-dory-1.0-4b","sources":["https://huggingface.co/nvidia/NVIDIA-Nemotron-Labs-Dory1.0-4B-BF16","https://huggingface.co/nvidia/NVIDIA-Nemotron-Labs-Dory1.0-4B-BF16/blob/main/config.json","https://huggingface.co/api/models/nvidia/NVIDIA-Nemotron-Labs-Dory1.0-4B-BF16","https://huggingface.co/snsnc/NVIDIA-Nemotron-Labs-Dory1.0-4B-mlx-4bit","https://huggingface.co/nvidia/NVIDIA-Nemotron-Labs-Dory1.0-4B-GGUF"]},{"model":"nemotron-3-nano-30b-a3b","name":"Nemotron 3 Nano 30B A3B","maker":"NVIDIA","hf_repo":"nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16","params_b":30,"active_params_b":3.5,"architecture":"moe","context_tokens":262144,"license":"NVIDIA Nemotron Open Model License","released":"2025-12-15","modality":"text","precision":"BF16 (official FP8 and NVFP4 repos)","repo_weights_gb":63.16,"native_gb":null,"native_bits":null,"offload_gb":null,"mlx_build":"mlx-community/NVIDIA-Nemotron-3-Nano-30B-A3B-4bit","page":"https://mlx.app/run/nemotron-3-nano-30b-a3b","sources":["https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16","https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16/blob/main/config.json"]},{"model":"nemotron-3.5-lightning-30b-a3b","name":"Nemotron 3.5 Lightning 30B A3B","maker":"NVIDIA","hf_repo":"nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16","params_b":30,"active_params_b":3,"architecture":"moe","context_tokens":262144,"license":"OpenMDW-1.1","released":"2026-08-11","modality":"text","precision":"BF16 (official NVFP4 repo)","repo_weights_gb":65.83,"native_gb":null,"native_bits":null,"offload_gb":null,"mlx_build":"mlx-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-4bit","page":"https://mlx.app/run/nemotron-3.5-lightning-30b-a3b","sources":["https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16","https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16/blob/main/config.json"]},{"model":"nemotron-3.5-bolt-74b-a9b","name":"Nemotron 3.5 Bolt 74B A9B","maker":"NVIDIA","hf_repo":"nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-BF16","params_b":74,"active_params_b":9,"architecture":"moe","context_tokens":262144,"license":"OpenMDW-1.1","released":"2026-10-15","modality":"text+image","precision":"BF16; official 24GB variant uses native 2-bit","repo_weights_gb":149.77,"native_gb":null,"native_bits":null,"offload_gb":null,"mlx_build":null,"page":"https://mlx.app/run/nemotron-3.5-bolt-74b-a9b","sources":["https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-BF16","https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-BF16/blob/main/config.json","https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB-GGUF"]},{"model":"nemotron-3-super-120b-a12b","name":"Nemotron 3 Super 120B A12B","maker":"NVIDIA","hf_repo":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","params_b":120,"active_params_b":12,"architecture":"moe","context_tokens":262144,"license":"NVIDIA Nemotron Open Model License","released":"2026-03-11","modality":"text","precision":"BF16 (official NVFP4 repo)","repo_weights_gb":247.23,"native_gb":null,"native_bits":null,"offload_gb":null,"mlx_build":"mlx-community/NVIDIA-Nemotron-3-Super-120B-A12B-4bit","page":"https://mlx.app/run/nemotron-3-super-120b-a12b","sources":["https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16","https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16/blob/main/config.json"]},{"model":"nemotron-3.5-super-vl-120b-a12b","name":"Nemotron 3.5 Super VL 120B A12B","maker":"NVIDIA","hf_repo":"nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16","params_b":120,"active_params_b":12,"architecture":"moe","context_tokens":1048576,"license":"OpenMDW-1.1","released":"2026-10-15","modality":"text+image+video","precision":"BF16 (official NVFP4 and NVFP4-LiLiCorr repos)","repo_weights_gb":248.91,"native_gb":null,"native_bits":null,"offload_gb":null,"mlx_build":"Duckets/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-MLX-4bit","page":"https://mlx.app/run/nemotron-3.5-super-vl-120b-a12b","sources":["https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16","https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16/blob/main/config.json","https://huggingface.co/api/models/nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16","https://huggingface.co/Duckets/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-MLX-4bit","https://huggingface.co/lmstudio-community/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-GGUF"]},{"model":"nemotron-3-ultra-550b-a55b","name":"Nemotron 3 Ultra 550B A55B","maker":"NVIDIA","hf_repo":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","params_b":550,"active_params_b":55,"architecture":"moe","context_tokens":262144,"license":"OpenMDW-1.1","released":"2026-06-04","modality":"text","precision":"BF16","repo_weights_gb":1121.06,"native_gb":null,"native_bits":null,"offload_gb":null,"mlx_build":"mlx-community/Nemotron-3-Ultra-550B-A55B-4bit","page":"https://mlx.app/run/nemotron-3-ultra-550b-a55b","sources":["https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16/blob/main/config.json"]},{"model":"gpt-oss-20b","name":"gpt-oss-20b","maker":"OpenAI","hf_repo":"openai/gpt-oss-20b","params_b":21,"active_params_b":3.6,"architecture":"moe","context_tokens":131072,"license":"Apache-2.0","released":"2025-08-04","modality":"text","precision":"MXFP4 (MoE weights, post-trained in MXFP4) + BF16 rest","repo_weights_gb":13.76,"native_gb":13.76,"native_bits":4.25,"offload_gb":null,"mlx_build":"mlx-community/gpt-oss-20b-MXFP4-Q8","page":"https://mlx.app/run/gpt-oss-20b","sources":["https://huggingface.co/openai/gpt-oss-20b","https://huggingface.co/openai/gpt-oss-20b/blob/main/config.json"]},{"model":"gpt-oss-120b","name":"gpt-oss-120b","maker":"OpenAI","hf_repo":"openai/gpt-oss-120b","params_b":117,"active_params_b":5.1,"architecture":"moe","context_tokens":131072,"license":"Apache-2.0","released":"2025-08-04","modality":"text","precision":"MXFP4 (MoE weights) + BF16 rest","repo_weights_gb":65.25,"native_gb":65.25,"native_bits":4.25,"offload_gb":null,"mlx_build":"mlx-community/gpt-oss-120b-MXFP4-Q8","page":"https://mlx.app/run/gpt-oss-120b","sources":["https://huggingface.co/openai/gpt-oss-120b","https://huggingface.co/openai/gpt-oss-120b/blob/main/config.json"]},{"model":"minicpm5-2b","name":"MiniCPM5 2B","maker":"OpenBMB","hf_repo":"openbmb/MiniCPM5-2B","params_b":2.52,"active_params_b":2.52,"architecture":"dense","context_tokens":131072,"license":"Apache-2.0","released":"2026-09-06","modality":"text","precision":"BF16","repo_weights_gb":5.03,"native_gb":null,"native_bits":null,"offload_gb":null,"mlx_build":"mlx-community/MiniCPM5-2B-mlx-4Bit","page":"https://mlx.app/run/minicpm5-2b","sources":["https://huggingface.co/openbmb/MiniCPM5-2B","https://huggingface.co/openbmb/MiniCPM5-2B/blob/main/config.json"]},{"model":"ornith-1.5-122b","name":"Ornith 1.5 122B","maker":"Ornith AI","hf_repo":"ornith-ai/Ornith-1.5-122B","params_b":122,"active_params_b":10,"architecture":"moe","context_tokens":262144,"license":"MIT","released":"2026-10-20","modality":"text+image","precision":"BF16","repo_weights_gb":null,"native_gb":null,"native_bits":null,"offload_gb":null,"mlx_build":null,"page":"https://mlx.app/run/ornith-1.5-122b","sources":["https://huggingface.co/ornith-ai/Ornith-1.5-122B","https://huggingface.co/ornith-ai/Ornith-1.5-122B/blob/main/config.json","https://huggingface.co/Qwen/Qwen3.5-122B-A10B/blob/main/config.json"]},{"model":"qwen3-0.6b","name":"Qwen3 0.6B","maker":"Qwen (Alibaba)","hf_repo":"Qwen/Qwen3-0.6B","params_b":0.6,"active_params_b":0.6,"architecture":"dense","context_tokens":40960,"license":"Apache-2.0","released":"2025-04-27","modality":"text","precision":"BF16","repo_weights_gb":1.5,"native_gb":null,"native_bits":null,"offload_gb":null,"mlx_build":"mlx-community/Qwen3-0.6B-4bit","page":"https://mlx.app/run/qwen3-0.6b","sources":["https://huggingface.co/Qwen/Qwen3-0.6B","https://huggingface.co/Qwen/Qwen3-0.6B/blob/main/config.json"]},{"model":"qwen3.5-0.8b","name":"Qwen3.5 0.8B","maker":"Qwen (Alibaba)","hf_repo":"Qwen/Qwen3.5-0.8B","params_b":0.8,"active_params_b":0.8,"architecture":"dense","context_tokens":262144,"license":"Apache-2.0","released":"2026-02-28","modality":"text+image+video","precision":"BF16","repo_weights_gb":1.75,"native_gb":null,"native_bits":null,"offload_gb":null,"mlx_build":"mlx-community/Qwen3.5-0.8B-4bit","page":"https://mlx.app/run/qwen3.5-0.8b","sources":["https://huggingface.co/Qwen/Qwen3.5-0.8B","https://huggingface.co/Qwen/Qwen3.5-0.8B/blob/main/config.json"]},{"model":"qwen3.5-2b","name":"Qwen3.5 2B","maker":"Qwen (Alibaba)","hf_repo":"Qwen/Qwen3.5-2B","params_b":2,"active_params_b":2,"architecture":"dense","context_tokens":262144,"license":"Apache-2.0","released":"2026-02-28","modality":"text+image+video","precision":"BF16","repo_weights_gb":4.55,"native_gb":null,"native_bits":null,"offload_gb":null,"mlx_build":"mlx-community/Qwen3.5-2B-MLX-4bit","page":"https://mlx.app/run/qwen3.5-2b","sources":["https://huggingface.co/Qwen/Qwen3.5-2B","https://huggingface.co/Qwen/Qwen3.5-2B/blob/main/config.json"]},{"model":"qwen3.5-4b","name":"Qwen3.5 4B","maker":"Qwen (Alibaba)","hf_repo":"Qwen/Qwen3.5-4B","params_b":4,"active_params_b":4,"architecture":"dense","context_tokens":262144,"license":"Apache-2.0","released":"2026-02-27","modality":"text+image+video","precision":"BF16","repo_weights_gb":9.32,"native_gb":null,"native_bits":null,"offload_gb":null,"mlx_build":"mlx-community/Qwen3.5-4B-MLX-4bit","page":"https://mlx.app/run/qwen3.5-4b","sources":["https://huggingface.co/Qwen/Qwen3.5-4B","https://huggingface.co/Qwen/Qwen3.5-4B/blob/main/config.json"]},{"model":"qwen3-8b","name":"Qwen3 8B","maker":"Qwen (Alibaba)","hf_repo":"Qwen/Qwen3-8B","params_b":8.2,"active_params_b":8.2,"architecture":"dense","context_tokens":40960,"license":"Apache-2.0","released":"2025-04-27","modality":"text","precision":"BF16","repo_weights_gb":16.38,"native_gb":null,"native_bits":null,"offload_gb":null,"mlx_build":"mlx-community/Qwen3-8B-4bit","page":"https://mlx.app/run/qwen3-8b","sources":["https://huggingface.co/Qwen/Qwen3-8B","https://huggingface.co/Qwen/Qwen3-8B/blob/main/config.json"]},{"model":"qwen3.5-9b","name":"Qwen3.5 9B","maker":"Qwen (Alibaba)","hf_repo":"Qwen/Qwen3.5-9B","params_b":9,"active_params_b":9,"architecture":"dense","context_tokens":262144,"license":"Apache-2.0","released":"2026-02-27","modality":"text+image+video","precision":"BF16","repo_weights_gb":19.31,"native_gb":null,"native_bits":null,"offload_gb":null,"mlx_build":"mlx-community/Qwen3.5-9B-MLX-4bit","page":"https://mlx.app/run/qwen3.5-9b","sources":["https://huggingface.co/Qwen/Qwen3.5-9B","https://huggingface.co/Qwen/Qwen3.5-9B/blob/main/config.json"]},{"model":"qwen3.8-27b","name":"Qwen3.8 27B","maker":"Qwen (Alibaba)","hf_repo":"Qwen/Qwen3.8-27B","params_b":27,"active_params_b":27,"architecture":"dense","context_tokens":262144,"license":"Apache-2.0","released":"2026-08-05","modality":"text+image+video","precision":"BF16","repo_weights_gb":55.56,"native_gb":null,"native_bits":null,"offload_gb":null,"mlx_build":"mlx-community/Qwen3.8-27B-4bit","page":"https://mlx.app/run/qwen3.8-27b","sources":["https://huggingface.co/Qwen/Qwen3.8-27B","https://huggingface.co/Qwen/Qwen3.8-27B/blob/main/config.json"]},{"model":"qwen3.6-27b","name":"Qwen3.6 27B","maker":"Qwen (Alibaba)","hf_repo":"Qwen/Qwen3.6-27B","params_b":27,"active_params_b":27,"architecture":"dense","context_tokens":262144,"license":"Apache-2.0","released":"2026-04-21","modality":"text+image+video","precision":"BF16","repo_weights_gb":55.56,"native_gb":null,"native_bits":null,"offload_gb":null,"mlx_build":"mlx-community/Qwen3.6-27B-4bit","page":"https://mlx.app/run/qwen3.6-27b","sources":["https://huggingface.co/Qwen/Qwen3.6-27B","https://huggingface.co/Qwen/Qwen3.6-27B/blob/main/config.json"]},{"model":"qwen3-coder-30b-a3b","name":"Qwen3 Coder 30B A3B Instruct","maker":"Qwen (Alibaba)","hf_repo":"Qwen/Qwen3-Coder-30B-A3B-Instruct","params_b":30.5,"active_params_b":3.3,"architecture":"moe","context_tokens":262144,"license":"Apache-2.0","released":"2025-07-31","modality":"text","precision":"BF16","repo_weights_gb":61.07,"native_gb":null,"native_bits":null,"offload_gb":null,"mlx_build":"mlx-community/Qwen3-Coder-30B-A3B-Instruct-4bit","page":"https://mlx.app/run/qwen3-coder-30b-a3b","sources":["https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct","https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct/blob/main/config.json"]},{"model":"qwen3.6-35b-a3b","name":"Qwen3.6 35B A3B","maker":"Qwen (Alibaba)","hf_repo":"Qwen/Qwen3.6-35B-A3B","params_b":35,"active_params_b":3,"architecture":"moe","context_tokens":262144,"license":"Apache-2.0","released":"2026-04-15","modality":"text+image+video","precision":"BF16","repo_weights_gb":71.9,"native_gb":null,"native_bits":null,"offload_gb":null,"mlx_build":"mlx-community/Qwen3.6-35B-A3B-4bit","page":"https://mlx.app/run/qwen3.6-35b-a3b","sources":["https://huggingface.co/Qwen/Qwen3.6-35B-A3B","https://huggingface.co/Qwen/Qwen3.6-35B-A3B/blob/main/config.json"]},{"model":"qwen3-coder-next","name":"Qwen3 Coder Next","maker":"Qwen (Alibaba)","hf_repo":"Qwen/Qwen3-Coder-Next","params_b":80,"active_params_b":3,"architecture":"moe","context_tokens":262144,"license":"Apache-2.0","released":"2026-01-30","modality":"text","precision":"BF16","repo_weights_gb":159.36,"native_gb":null,"native_bits":null,"offload_gb":null,"mlx_build":"mlx-community/Qwen3-Coder-Next-4bit","page":"https://mlx.app/run/qwen3-coder-next","sources":["https://huggingface.co/Qwen/Qwen3-Coder-Next","https://huggingface.co/Qwen/Qwen3-Coder-Next/blob/main/config.json"]},{"model":"qwen3.5-122b-a10b","name":"Qwen3.5 122B A10B","maker":"Qwen (Alibaba)","hf_repo":"Qwen/Qwen3.5-122B-A10B","params_b":122,"active_params_b":10,"architecture":"moe","context_tokens":262144,"license":"Apache-2.0","released":"2026-02-24","modality":"text+image+video","precision":"BF16","repo_weights_gb":250.17,"native_gb":null,"native_bits":null,"offload_gb":null,"mlx_build":"mlx-community/Qwen3.5-122B-A10B-4bit","page":"https://mlx.app/run/qwen3.5-122b-a10b","sources":["https://huggingface.co/Qwen/Qwen3.5-122B-A10B","https://huggingface.co/Qwen/Qwen3.5-122B-A10B/blob/main/config.json"]},{"model":"qwen3.8-flash-next","name":"Qwen3.8 Flash Next","maker":"Qwen (Alibaba)","hf_repo":"Qwen/Qwen3.8-Flash-Next","params_b":180,"active_params_b":6,"architecture":"moe","context_tokens":262144,"license":"Qwen Community License 1.0 (qwen-community-1.0)","released":"2026-08-24","modality":"text+image+video","precision":"BF16","repo_weights_gb":360,"native_gb":null,"native_bits":null,"offload_gb":null,"mlx_build":"mlx-community/Qwen3.8-Flash-Next-4bit","page":"https://mlx.app/run/qwen3.8-flash-next","sources":["https://huggingface.co/Qwen/Qwen3.8-Flash-Next","https://huggingface.co/Qwen/Qwen3.8-Flash-Next/blob/main/config.json"]},{"model":"qwen3.5-397b-a17b","name":"Qwen3.5 397B A17B","maker":"Qwen (Alibaba)","hf_repo":"Qwen/Qwen3.5-397B-A17B","params_b":397,"active_params_b":17,"architecture":"moe","context_tokens":262144,"license":"Apache-2.0","released":"2026-02-16","modality":"text+image+video","precision":"BF16","repo_weights_gb":806.8,"native_gb":null,"native_bits":null,"offload_gb":null,"mlx_build":"mlx-community/Qwen3.5-397B-A17B-4bit","page":"https://mlx.app/run/qwen3.5-397b-a17b","sources":["https://huggingface.co/Qwen/Qwen3.5-397B-A17B","https://huggingface.co/Qwen/Qwen3.5-397B-A17B/blob/main/config.json"]},{"model":"qwen3.8-2.4t-a95b","name":"Qwen3.8 2.4T A95B","maker":"Qwen (Alibaba)","hf_repo":"Qwen/Qwen3.8-2.4T-A95B","params_b":2400,"active_params_b":95,"architecture":"moe","context_tokens":262144,"license":"Qwen3.8-Max license (qwen3.8-max)","released":"2026-08-08","modality":"text","precision":"BF16","repo_weights_gb":4892.37,"native_gb":null,"native_bits":null,"offload_gb":null,"mlx_build":null,"page":"https://mlx.app/run/qwen3.8-2.4t-a95b","sources":["https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B","https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/main/config.json"]},{"model":"flint","name":"Recursive Flint","maker":"Recursive","hf_repo":"RecursiveSI/flint","params_b":39.8,"active_params_b":2.5,"architecture":"moe","context_tokens":262144,"license":"Apache-2.0","released":"2026-10-21","modality":"text","precision":"BF16 (HF metadata: 39.79B BF16); official MLX INT4, INT4 GGUF and NVFP4 GGUF repos","repo_weights_gb":79.58,"native_gb":null,"native_bits":null,"offload_gb":null,"mlx_build":"RecursiveSI/flint-int4","page":"https://mlx.app/run/flint","sources":["https://huggingface.co/RecursiveSI/flint","https://huggingface.co/RecursiveSI/flint/blob/main/config.json","https://huggingface.co/api/models/RecursiveSI/flint","https://huggingface.co/RecursiveSI/flint-int4","https://huggingface.co/RecursiveSI/flint-int4-gguf","https://www.recursive.com/updates/introducing-recursive-flint","https://github.com/recursive-oss/rec"]},{"model":"beam-1.0","name":"Beam 1.0","maker":"Reflection AI","hf_repo":"reflection/Beam-1.0-501B-A23B","params_b":501,"active_params_b":23,"architecture":"moe","context_tokens":1048576,"license":"Apache-2.0","released":"2026-10-07","modality":"text","precision":"BF16 (FP8 and NVFP4 also released per card)","repo_weights_gb":1002.67,"native_gb":null,"native_bits":null,"offload_gb":null,"mlx_build":null,"page":"https://mlx.app/run/beam-1.0","sources":["https://huggingface.co/reflection/Beam-1.0-501B-A23B","https://huggingface.co/reflection/Beam-1.0-501B-A23B/blob/main/config.json"]},{"model":"sage-a1.5","name":"Sage-A1.5","maker":"Shanghai AI Laboratory (InternScience)","hf_repo":"InternScience/Sage-A1.5","params_b":35,"active_params_b":2.95,"architecture":"moe","context_tokens":262144,"license":"Apache-2.0","released":"2026-10-21","modality":"text+image","precision":"BF16 (HF metadata: 35.95B BF16); official FP8 and GGUF (Q4_K_M, Q8_0, F16) repos","repo_weights_gb":71.91,"native_gb":null,"native_bits":null,"offload_gb":null,"mlx_build":"mlx-community/Sage-A1.5-OptiQ-4bit","page":"https://mlx.app/run/sage-a1.5","sources":["https://huggingface.co/InternScience/Sage-A1.5","https://huggingface.co/InternScience/Sage-A1.5/blob/main/config.json","https://huggingface.co/api/models/InternScience/Sage-A1.5","https://huggingface.co/mlx-community/Sage-A1.5-OptiQ-4bit","https://huggingface.co/InternScience/Sage-A1.5-Q4_K_M-GGUF","https://arxiv.org/abs/2610.28578"]},{"model":"spark-x2.6-4b","name":"Spark-X2.6 4B","maker":"SparkLLM (XHToken)","hf_repo":"XHToken/Spark-X2.6-4B","params_b":4.11,"active_params_b":4.11,"architecture":"dense","context_tokens":1048576,"license":"Apache-2.0","released":"2026-10-19","modality":"text","precision":"BF16 (HF metadata: 4.11B BF16); official GGUF (Q4_K_M, Q8_0, BF16), FP8, INT8 and INT4 repos","repo_weights_gb":8.22,"native_gb":null,"native_bits":null,"offload_gb":null,"mlx_build":"abenzerps/Spark-X2.6-4B-MLX-4bit","page":"https://mlx.app/run/spark-x2.6-4b","sources":["https://huggingface.co/XHToken/Spark-X2.6-4B","https://huggingface.co/XHToken/Spark-X2.6-4B/blob/main/config.json","https://huggingface.co/api/models/XHToken/Spark-X2.6-4B","https://huggingface.co/XHToken/Spark-X2.6-4B-Base","https://huggingface.co/abenzerps/Spark-X2.6-4B-MLX-4bit","https://huggingface.co/XHToken/Spark-X2.6-4B-GGUF","https://github.com/XHToken/Spark-MLX-LLM"]},{"model":"step-3.7-flash","name":"Step 3.7 Flash","maker":"StepFun","hf_repo":"stepfun-ai/Step-3.7-Flash","params_b":198,"active_params_b":null,"architecture":"moe","context_tokens":262144,"license":"Apache-2.0","released":"2026-05-23","modality":"text+image","precision":"BF16 (official FP8/NVFP4/GGUF repos)","repo_weights_gb":402.73,"native_gb":null,"native_bits":null,"offload_gb":null,"mlx_build":"mlx-community/Step-3.7-Flash-4bit","page":null,"sources":["https://huggingface.co/stepfun-ai/Step-3.7-Flash","https://huggingface.co/stepfun-ai/Step-3.7-Flash/blob/main/config.json"]},{"model":"hy-memory-30b-a3b","name":"Hy-Memory-30B-A3B","maker":"Tencent","hf_repo":"tencent/Hy-Memory-30B-A3B","params_b":30.06,"active_params_b":3.2,"architecture":"moe","context_tokens":262144,"license":"Apache-2.0","released":"2026-10-15","modality":"text","precision":"BF16 (HF metadata: 30.06B BF16); official FP8 and GGUF repos","repo_weights_gb":60.13,"native_gb":null,"native_bits":null,"offload_gb":null,"mlx_build":"mlx-community/Hy-Memory-30B-A3B-4bit","page":"https://mlx.app/run/hy-memory-30b-a3b","sources":["https://huggingface.co/tencent/Hy-Memory-30B-A3B","https://huggingface.co/tencent/Hy-Memory-30B-A3B/blob/main/config.json","https://huggingface.co/api/models/tencent/Hy-Memory-30B-A3B","https://huggingface.co/mlx-community/Hy-Memory-30B-A3B-4bit","https://huggingface.co/tencent/Hy-Memory-30B-A3B-GGUF","https://arxiv.org/abs/2610.22196"]},{"model":"hy3","name":"Hy3","maker":"Tencent","hf_repo":"tencent/Hy3","params_b":295,"active_params_b":21,"architecture":"moe","context_tokens":262144,"license":"Apache-2.0","released":"2026-07-02","modality":"text","precision":"BF16 (official FP8 repo)","repo_weights_gb":597.58,"native_gb":null,"native_bits":null,"offload_gb":null,"mlx_build":"mlx-community/Hy3-OptiQ-2bit","page":"https://mlx.app/run/hy3","sources":["https://huggingface.co/tencent/Hy3","https://huggingface.co/tencent/Hy3/blob/main/config.json"]},{"model":"inkling-small","name":"Inkling Small","maker":"Thinking Machines Lab","hf_repo":"thinkingmachines/Inkling-Small","params_b":276,"active_params_b":12,"architecture":"moe","context_tokens":null,"license":"Apache-2.0","released":"2026-07-27","modality":"text+image+audio","precision":"BF16 (official NVFP4 repo)","repo_weights_gb":531.91,"native_gb":null,"native_bits":null,"offload_gb":null,"mlx_build":"mlx-community/Inkling-Small-mlx-4bit","page":"https://mlx.app/run/inkling-small","sources":["https://huggingface.co/thinkingmachines/Inkling-Small","https://huggingface.co/thinkingmachines/Inkling-Small/blob/main/config.json","https://huggingface.co/blog/thinkingmachines-inkling"]},{"model":"inkling","name":"Inkling","maker":"Thinking Machines Lab","hf_repo":"thinkingmachines/Inkling","params_b":975,"active_params_b":41,"architecture":"moe","context_tokens":null,"license":"Apache-2.0","released":"2026-07-14","modality":"text+image+audio","precision":"BF16 (official NVFP4 repo)","repo_weights_gb":1904.76,"native_gb":null,"native_bits":null,"offload_gb":null,"mlx_build":"mlx-community/Inkling-mlx-4bit","page":"https://mlx.app/run/inkling","sources":["https://huggingface.co/thinkingmachines/Inkling","https://huggingface.co/thinkingmachines/Inkling/blob/main/config.json","https://huggingface.co/blog/thinkingmachines-inkling"]},{"model":"mimo-v2.6-flash","name":"MiMo V2.6 Flash","maker":"Xiaomi","hf_repo":"XiaomiMiMo/MiMo-V2.6-Flash-RL","params_b":309,"active_params_b":15,"architecture":"moe","context_tokens":1048576,"license":"MIT","released":"2026-09-21","modality":"text+image+video+audio","precision":"MXFP4 experts (store_dtype mxfp4) + FP8 (config)","repo_weights_gb":172.93,"native_gb":172.93,"native_bits":null,"offload_gb":null,"mlx_build":"mlx-community/MiMo-V2.6-Flash-RL-mxfp4-q8","page":"https://mlx.app/run/mimo-v2.6-flash","sources":["https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL","https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL/blob/main/config.json"]},{"model":"mimo-v2.6-pro","name":"MiMo V2.6 Pro","maker":"Xiaomi","hf_repo":"XiaomiMiMo/MiMo-V2.6-Pro-RL","params_b":1020,"active_params_b":42,"architecture":"moe","context_tokens":1048576,"license":"MIT","released":"2026-09-21","modality":"text+image+video+audio","precision":"MXFP4 experts + FP8 (config)","repo_weights_gb":566.05,"native_gb":566.05,"native_bits":null,"offload_gb":null,"mlx_build":"mlx-community/MiMo-V2.6-Pro-RL-mxfp4-q8","page":"https://mlx.app/run/mimo-v2.6-pro","sources":["https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Pro-RL","https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Pro-RL/blob/main/config.json"]},{"model":"glm-4.7-flash","name":"GLM-4.7 Flash","maker":"Z.ai (Zhipu)","hf_repo":"zai-org/GLM-4.7-Flash","params_b":30,"active_params_b":3,"architecture":"moe","context_tokens":202752,"license":"MIT","released":"2026-01-19","modality":"text","precision":"BF16","repo_weights_gb":62.44,"native_gb":null,"native_bits":null,"offload_gb":null,"mlx_build":"mlx-community/GLM-4.7-Flash-4bit","page":"https://mlx.app/run/glm-4.7-flash","sources":["https://huggingface.co/zai-org/GLM-4.7-Flash","https://huggingface.co/zai-org/GLM-4.7-Flash/blob/main/config.json"]},{"model":"glm-4.5-air","name":"GLM-4.5 Air","maker":"Z.ai (Zhipu)","hf_repo":"zai-org/GLM-4.5-Air","params_b":106,"active_params_b":12,"architecture":"moe","context_tokens":131072,"license":"MIT","released":"2025-07-20","modality":"text","precision":"BF16 (official FP8 repo exists)","repo_weights_gb":220.94,"native_gb":null,"native_bits":null,"offload_gb":null,"mlx_build":"mlx-community/GLM-4.5-Air-4bit","page":"https://mlx.app/run/glm-4.5-air","sources":["https://huggingface.co/zai-org/GLM-4.5-Air","https://huggingface.co/zai-org/GLM-4.5-Air/blob/main/config.json"]},{"model":"glm-5.3-flash","name":"GLM-5.3 Flash","maker":"Z.ai (Zhipu)","hf_repo":"zai-org/GLM-5.3-Flash","params_b":320,"active_params_b":18,"architecture":"moe","context_tokens":1048576,"license":"MIT","released":"2026-08-25","modality":"text+image","precision":"FP8 (repo); BF16 repo zai-org/GLM-5.3-Flash-BF16","repo_weights_gb":328.34,"native_gb":null,"native_bits":null,"offload_gb":null,"mlx_build":"mlx-community/GLM-5.3-Flash-4bit","page":"https://mlx.app/run/glm-5.3-flash","sources":["https://huggingface.co/zai-org/GLM-5.3-Flash","https://huggingface.co/zai-org/GLM-5.3-Flash/blob/main/config.json"]},{"model":"glm-5.3","name":"GLM-5.3","maker":"Z.ai (Zhipu)","hf_repo":"zai-org/GLM-5.3","params_b":744,"active_params_b":40,"architecture":"moe","context_tokens":1048576,"license":"GLM-5.3 license (custom, 'glm-5.3')","released":"2026-08-25","modality":"text","precision":"FP8 (repo); BF16 repo zai-org/GLM-5.3-BF16","repo_weights_gb":755.63,"native_gb":null,"native_bits":null,"offload_gb":null,"mlx_build":"mlx-community/GLM-5.3-4bit","page":"https://mlx.app/run/glm-5.3","sources":["https://huggingface.co/zai-org/GLM-5.3","https://huggingface.co/zai-org/GLM-5.3/blob/main/config.json","https://huggingface.co/zai-org/GLM-5","https://huggingface.co/zai-org/GLM-5/blob/main/config.json","https://huggingface.co/zai-org/GLM-5.2"]}]}