| Model | Laki | Sa 4-bit | Pinakamaliit na Mac |
|---|---|---|---|
| Qwen3 0.6BQwen (Alibaba) | 0.6B | 1.8 GB | 8 GB |
| Qwen3.5 0.8BQwen (Alibaba) | 0.8B | 2 GB | 8 GB |
| Llama 3.2 1B InstructMeta | 1.23B | 2.2 GB | 8 GB |
| Qwen3.5 2BQwen (Alibaba) | 2B | 2.6 GB | 8 GB |
| MiniCPM5 2BOpenBMB | 2.52B | 2.9 GB | 8 GB |
| LFM2.5 2.6BLiquid AI | 2.69B | 3 GB | 8 GB |
| Granite 4.2 3BIBM | 3B | 3.2 GB | 8 GB |
| SmolLM3 3BHugging Face | 3B | 3.2 GB | 8 GB |
| Llama 3.2 3B InstructMeta | 3.21B | 3.3 GB | 8 GB |
| Phi-4 mini instructMicrosoft | 3.8B | 3.6 GB | 8 GB |
| Nemotron 3 Nano 4BNVIDIA | 3.97B | 3.7 GB | 8 GB |
| Qwen3.5 4BQwen (Alibaba) | 4B | 3.8 GB | 8 GB |
| Gemma 4 E2BGoogle DeepMind | 5.1B | 4.4 GB | 8 GB |
| Llama 3.1 8B InstructMeta | 8B | 6 GB | 8 GB |
| Gemma 4 E4BGoogle DeepMind | 8B | 6 GB | 8 GB |
| Granite 4.2 8BIBM | 8B | 6 GB | 8 GB |
| Qwen3 8BQwen (Alibaba) | 8.2B | 6.1 GB | 16 GB |
| Ministral 3 8BMistral AI | 8.9B | 6.5 GB | 16 GB |
| Qwen3.5 9BQwen (Alibaba) | 9B | 6.6 GB | 16 GB |
| Gemma 4 12B UnifiedGoogle DeepMind | 12B | 8.2 GB | 16 GB |
| Phi-4 (14B)Microsoft | 14B | 9.4 GB | 16 GB |
| Phi-4 Reasoning Vision 15BMicrosoft | 15B | 9.9 GB | 16 GB |
| gpt-oss-20bOpenAI | 21B · 3.6B aktibo | 15.3 GB | 24 GB |
| Devstral Small 2 (24B)Mistral AI | 24B | 15 GB | 24 GB |
| Magistral Small 1.2 (2509)Mistral AI | 24B | 15 GB | 24 GB |
| Mistral Small 3.2 (24B)Mistral AI | 24B | 15 GB | 24 GB |
| LFM2.5 24B A2BLiquid AI | 24B · 2B aktibo | 15 GB | 24 GB |
| Gemma 4 26B A4BGoogle DeepMind | 25.2B · 3.8B aktibo | 15.7 GB | 24 GB |
| Qwen3.8 27BQwen (Alibaba) | 27B | 16.7 GB | 24 GB |
| Qwen3.6 27BQwen (Alibaba) | 27B | 16.7 GB | 24 GB |
| Muse Glimmer 30BMeta (Meta Superintelligence Lab) | 29.6B | 18.2 GB | 32 GB |
| GLM-4.7 FlashZ.ai (Zhipu) | 30B · 3B aktibo | 18.4 GB | 32 GB |
| Nemotron 3 Nano 30B A3BNVIDIA | 30B · 3.5B aktibo | 18.4 GB | 32 GB |
| Nemotron 3.5 Lightning 30B A3BNVIDIA | 30B · 3B aktibo | 18.4 GB | 32 GB |
| Granite 4.2 30BIBM | 30B | 18.4 GB | 32 GB |
| Qwen3 Coder 30B A3B InstructQwen (Alibaba) | 30.5B · 3.3B aktibo | 18.7 GB | 32 GB |
| Gemma 4 31BGoogle DeepMind | 30.7B | 18.8 GB | 32 GB |
| Qwen3.6 35B A3BQwen (Alibaba) | 35B · 3B aktibo | 21.3 GB | 32 GB |
| Llama 3.3 70B InstructMeta | 70B | 42.6 GB | 64 GB |
| Nemotron 3.5 Bolt 74B A9BNVIDIA | 74B · 9B aktibo | 44.9 GB | 64 GB |
| Qwen3 Coder NextQwen (Alibaba) | 80B · 3B aktibo | 48.6 GB | 96 GB |
| GLM-4.5 AirZ.ai (Zhipu) | 106B · 12B aktibo | 64.4 GB | 96 GB |
| Llama 4 Scout 17B-16E InstructMeta | 109B · 17B aktibo | 66.2 GB | 96 GB |
| gpt-oss-120bOpenAI | 117B · 5.1B aktibo | 70.5 GB | 96 GB |
| Mistral Small 4 (119B)Mistral AI | 119B · 6.5B aktibo | 72.3 GB | 128 GB |
| Nemotron 3 Super 120B A12BNVIDIA | 120B · 12B aktibo | 72.9 GB | 128 GB |
| Qwen3.5 122B A10BQwen (Alibaba) | 122B · 10B aktibo | 74.1 GB | 128 GB |
| Ornith 1.5 122BOrnith AI | 122B · 10B aktibo | 74.1 GB | 128 GB |
| Devstral 2 (123B)Mistral AI | 123B | 74.7 GB | 128 GB |
| Mistral Medium 3.5 (128B)Mistral AI | 128B | 77.8 GB | 128 GB |
| Qwen3.8 Flash NextQwen (Alibaba) | 180B · 6B aktibo | 109 GB | 192 GB |
| MiniMax M2.7MiniMax | 230B · 10B aktibo | 140 GB | 192 GB |
| Inkling SmallThinking Machines Lab | 276B · 12B aktibo | 168 GB | 256 GB |
| DeepSeek V4 Flash 0731DeepSeek | 284B · 13B aktibo | 173 GB | 256 GB |
| Hy3Tencent | 295B · 21B aktibo | 179 GB | 256 GB |
| MiMo V2.6 FlashXiaomi | 309B · 15B aktibo | 187 GB | 256 GB |
| GLM-5.3 FlashZ.ai (Zhipu) | 320B · 18B aktibo | 194 GB | 512 GB |
| Qwen3.5 397B A17BQwen (Alibaba) | 397B · 17B aktibo | 241 GB | 512 GB |
| Llama 4 Maverick 17B-128E InstructMeta | 400B · 17B aktibo | 243 GB | 512 GB |
| MiniMax M3MiniMax | 428B · 23B aktibo | 260 GB | 512 GB |
| Beam 1.0Reflection AI | 501B · 23B aktibo | 304 GB | 512 GB |
| Nemotron 3 Ultra 550B A55BNVIDIA | 550B · 55B aktibo | 334 GB | 512 GB |
| DeepSeek V4.1 Flash 1017DeepSeek | 552B · 16B aktibo | 335 GB | 512 GB |
| Mistral Large 3 (675B)Mistral AI | 675B · 41B aktibo | 410 GB | 512 GB |
| GLM-5.3Z.ai (Zhipu) | 744B · 40B aktibo | 452 GB | 512 GB |
| Muse Spark OpenMeta (Meta Superintelligence Labs) | 816B · 42B aktibo | 496 GB | 512 GB |
| InklingThinking Machines Lab | 975B · 41B aktibo | 592 GB | 512 GB |
| Kimi K2.6Moonshot AI | 1,000B · 32B aktibo | 643 GB | 512 GB |
| Kimi K2.7 CodeMoonshot AI | 1,000B · 32B aktibo | 643 GB | 512 GB |
| MiMo V2.6 ProXiaomi | 1,020B · 42B aktibo | 611 GB | 512 GB |
| DeepSeek V4 Pro 0813DeepSeek | 1,600B · 49B aktibo | 972 GB | wala |
| Qwen3.8 2.4T A95BQwen (Alibaba) | 2,400B · 95B aktibo | 1.5 TB | wala |
| Kimi K3Moonshot AI | 2,800B · 104B aktibo | 1.7 TB | wala |
O magsimula sa Mac mo: bawat Mac · paghambingin
Paano ito kinuwenta
Memory: ang mga parameter ng model sa 8, 6, 4, 3 o 2 bit kada weight dagdag ang group scales ng MLX (kalahating bit kada weight), o ang native format nito, at may espasyo pa para sa context. Bilang default, mga 75% ng unified memory ang ipinapagamit ng macOS sa GPU. Bilis: ang memory bandwidth na hinati sa mga byte na binabasa kada token ang pinakamataas na posible para sa isang usapan; sa mga pampublikong benchmark ng llama.cpp sa Apple Silicon, umaabot ang totoong takbo sa mga 45% hanggang 80% nito, at iyon ang range na ipinapakita. Mga tantiya ito, hindi sukat: sukatin ang sarili mong Mac sa MLX Bench. Ang mga numero ng model ay mula sa opisyal na model card ng bawat isa, at ang sa chip ay mula sa Tech Specs ng Apple. Sinuri noong 2026-10-19. Parehong data ng mlx.app/compare.