Log inCreate wallet

What can an M2 Ultra with 192 GB run?

49 of 73 open models run well on it. The GPU can use about 144 GB of its 192 GB by default, and it reads memory at 800 GB/s, which sets how fast it writes. Found in: Mac Studio (2023), Mac Pro (2023), Mac Pro (Rack, 2023).

Smartest that runs wellQwen3.8 Flash Next4-bit · 101 GB · 106–188 tok/sBiggest that runs wellMiniMax M2.74-bit · 129 GB · 64–114 tok/sFor codeQwen3 Coder Next8-bit · 85 GB · 113–200 tok/s

Runs well 56

Fits with room for context, at 10 or more tokens a second.

ModelVersionMemoryTokens/s
Qwen3.8 Flash Next180B · 6B active · Intelligence 39.84-bit101 GB106–188
Qwen3.8 27B27B · Intelligence 33.78-bit28.7 GB13–22
Nemotron 3.5 Bolt 74B A9B74B · 9B active · Intelligence 21.48-bit78.6 GB38–67
Qwen3.6 35B A3B35B · 3B active · Intelligence 18.28-bit37.2 GB113–200
Muse Glimmer 30B29.6B · Intelligence 17.58-bit31.5 GB11–20
Qwen3.5 122B A10B122B · 10B active · Intelligence 15.68-bit130 GB34–60
Gemma 4 31B30.7B · Intelligence 14.78-bit32.6 GB11–20
Nemotron 3.5 Lightning 30B A3B30B · 3B active · Intelligence 12.98-bit31.9 GB113–200
Granite 4.2 30B30B · Intelligence 12.78-bit31.9 GB11–20
MiniCPM5 2B2.52B · Intelligence 12.58-bit2.7 GB133–237
gpt-oss-120b117B · 5.1B active · Intelligence 11.6native 4.25-bit65.3 GB133–237
Mistral Small 4 (119B)119B · 6.5B active · Intelligence 11.38-bit126 GB52–93
Qwen3.5 9B9B · Intelligence 11.28-bit9.6 GB38–67
Granite 4.2 8B8B · Intelligence 11.18-bit8.5 GB42–75
Qwen3 Coder Next80B · 3B active · Intelligence 9.28-bit85 GB113–200
Granite 4.2 3B3B · Intelligence 9.18-bit3.2 GB113–200
gpt-oss-20b21B · 3.6B active · Intelligence 9native 4.25-bit13.8 GB189–337
Nemotron 3 Nano 30B A3B30B · 3.5B active · Intelligence 8.98-bit31.9 GB97–173
Gemma 4 E4B8B · Intelligence 8.98-bit8.5 GB75–133
Llama 4 Scout 17B-16E Instruct109B · 17B active · Intelligence 6.58-bit116 GB20–35
Ministral 3 8B8.9B · Intelligence 5.58-bit9.5 GB38–67
Nemotron 3 Nano 4B3.97B · Intelligence 4.88-bit4.2 GB86–152
MiniMax M2.7230B · 10B active4-bit129 GB64–114
Ornith 1.5 122B122B · 10B active8-bit130 GB34–60
Nemotron 3 Super 120B A12B120B · 12B active8-bit128 GB28–50
GLM-4.5 Air106B · 12B active8-bit113 GB28–50
Qwen3 Coder 30B A3B Instruct30.5B · 3.3B active8-bit32.4 GB103–183
GLM-4.7 Flash30B · 3B active8-bit31.9 GB113–200
Qwen3.6 27B27B8-bit28.7 GB13–22
Gemma 4 26B A4B25.2B · 3.8B active8-bit26.8 GB90–160
Devstral Small 2 (24B)24B8-bit25.5 GB14–25
Magistral Small 1.2 (2509)24B8-bit25.5 GB14–25
Mistral Small 3.2 (24B)24B8-bit25.5 GB14–25
LFM2.5 24B A2B24B · 2B active8-bit25.5 GB171–305
Phi-4 Reasoning Vision 15B15B8-bit15.9 GB23–40
Phi-4 (14B)14B8-bit14.9 GB24–43
Gemma 4 12B Unified12B8-bit12.7 GB28–50
Qwen3 8B8.2B8-bit8.7 GB41–74
Llama 3.1 8B Instruct8B8-bit8.5 GB42–75
Gemma 4 E2B5.1B8-bit5.4 GB150–267
Qwen3.5 4B4B8-bit4.3 GB84–149
Phi-4 mini instruct3.8B8-bit4 GB90–160
Llama 3.2 3B Instruct3.21B8-bit3.4 GB106–188
SmolLM3 3B3B8-bit3.2 GB113–200
LFM2.5 2.6B2.69B8-bit2.9 GB124–221
Qwen3.5 2B2B8-bit2.1 GB171–305
Llama 3.2 1B Instruct1.23B8-bit1.3 GB277–492
Qwen3.5 0.8B0.8B8-bit0.9 GB400–711
Qwen3 0.6B0.6B8-bit0.6 GB600–1067
GLM-5.3 Flash320B · 18B active · Intelligence 41.82-bit lower quality100 GB64–114
MiMo V2.6 Flash309B · 15B active · Intelligence 37.92-bit lower quality96.6 GB77–136
Inkling Small276B · 12B active · Intelligence 25.73-bit lower quality121 GB68–121
Hy3295B · 21B active · Intelligence 25.33-bit lower quality129 GB39–70
Qwen3.5 397B A17B397B · 17B active · Intelligence 18.42-bit lower quality124 GB68–121
Llama 4 Maverick 17B-128E Instruct400B · 17B active · Intelligence 9.32-bit lower quality125 GB68–121
DeepSeek V4 Flash 0731284B · 13B active3-bit lower quality124 GB63–112

Runs, but slowly 3

Fits, but under 10 tokens a second: fine for batch work, slow for chat.

ModelVersionMemoryTokens/s
Mistral Medium 3.5 (128B)128B · Intelligence 14.26-bit104 GB3–6
Devstral 2 (123B)123B8-bit131 GB3–5
Llama 3.3 70B Instruct70B8-bit74.4 GB5–9

Only just fits 2

Needs almost all memory: raise the GPU memory limit and keep the context short.

ModelVersionMemoryTokens/s
Beam 1.0501B · 23B active · Intelligence 30.32-bit lower quality157 GB50–89
MiniMax M3428B · 23B active · Intelligence 29.22-bit lower quality134 GB50–89

Too big 12

Needs more memory than 192 GB, even at 2 bits.

Other Macs

Every Mac with 192 GB, from any chip.

The M2 Ultra with more or less memory:

Neighbouring chips:

Head to head:

Compare it with any Mac or GPU · The M2 Ultra for local AI · The best Mac for local LLMs · Every Mac

Questions

What is the best LLM for an M2 Ultra with 192 GB?
Of the models with a published Intelligence Index, Qwen3.8 Flash Next scores highest among those that run well here: 4-bit, about 106–188 tokens a second. The biggest that runs well is MiniMax M2.7.
Can an M2 Ultra with 192 GB run Llama 3.3 70B?
Yes, but slowly: 8-bit, at about 5–9 tokens a second.
How fast is gpt-oss-20b on an M2 Ultra?
About 189–337 tokens a second (native 4.25-bit), from the chip’s 800 GB/s memory bandwidth.

Run them with MLX Harness (free, open source) or Apple’s mlx-lm in Terminal: step by step.

How it’s worked out

Memory: the model’s parameters at 8, 6, 4, 3 or 2 bits per weight plus MLX’s group scales (half a bit per weight), or its native format, with room for the context on top. By default macOS lets the GPU use about 75% of unified memory. Speed: memory bandwidth divided by the bytes read per token is the ceiling for one conversation; in llama.cpp’s public Apple Silicon benchmarks real runs reach about 45% to 80% of it, which is the range shown. These are estimates, not measurements: measure your own Mac on MLX Bench. Model figures from each official model card, chip figures from Apple’s Tech Specs. Checked 2026-10-19. Same data as mlx.app/compare.

What LLMs can an M2 Ultra with 192 GB run? Models and speed