RunsLocalGPU checker Local AI toolsv1.8 · data Oct 14, 2026

What AI models can the M3 Ultra 256GB run?

With 256 GB unified memory, the M3 Ultra 256GB runs 20 of 22 popular open models fully in fast memory at Q4_K_M or better (8K context). The largest that fit are Qwen3.8-Flash-Next (Q6_K), Qwen3.5 122B-A10B (Q8_0), gpt-oss-120b (Q8_0). Fastest: Gemma 4 E2B at over 150 tokens/sec and Qwen3.6 35B-A3B at over 150 tokens/sec.

Check with your own RAM and context length

Model	Result	Best quant	Memory needed	Est. speed
Gemma 4 E2B small	Runs on GPU	Q8_0	6.1 GB	150+ tok/s
Qwen3.6 35B-A3B MoE · coding	Runs on GPU	Q8_0	38.2 GB	150+ tok/s
gpt-oss-20b MoE · reasoning	Runs on GPU	Q8_0	23.2 GB	128 tok/s
Ministral 3 3B small	Runs on GPU	Q8_0	4.8 GB	122 tok/s
Gemma 4 26B A4B MoE · vision	Runs on GPU	Q8_0	27.9 GB	122 tok/s
Gemma 4 E4B small · audio	Runs on GPU	Q8_0	9.3 GB	103 tok/s
Qwen3.8-Flash-Next MoE	Runs on GPU	Q6_K	145.4 GB	100 tok/s
gpt-oss-120b MoE · reasoning	Runs on GPU	Q8_0	125.4 GB	91 tok/s
Qwen3.5 9B general	Runs on GPU	Q8_0	11.3 GB	48 tok/s
Qwen3.5 122B-A10B MoE	Runs on GPU	Q8_0	130.9 GB	46 tok/s
Gemma 4 12B general · audio	Runs on GPU	Q8_0	13.8 GB	39 tok/s
Phi-4 14B reasoning	Runs on GPU	Q8_0	17.7 GB	31 tok/s
Llama 4 Scout MoE · vision	Runs on GPU	Q8_0	117.8 GB	27 tok/s
Mistral Small 3.1 24B general	Runs on GPU	Q8_0	27.3 GB	19 tok/s
Qwen3.6 27B coding	Runs on GPU	Q8_0	29.8 GB	17 tok/s
Qwen3.8 27B coding	Runs on GPU	Q8_0	30.6 GB	17 tok/s
Granite 4.2 30B general	Runs on GPU	Q8_0	31.9 GB	16 tok/s
Gemma 4 31B general · vision	Runs on GPU	Q8_0	33.8 GB	15 tok/s
Hermes 4.3 36B general	Runs on GPU	Q8_0	40.5 GB	13 tok/s
Llama 3.3 70B general	Runs on GPU	Q8_0	78.1 GB	6.6 tok/s
GLM-5.3-Flash MoE · coding	Lower quality fit	Q3_K_M	158.4 GB	56 tok/s
DeepSeek V4.1-Flash MoE · coding	Too big	Q4_K_M	335.8 GB	—

Specs used: 256 GB unified memory, 819 GB/s memory bandwidth. Speeds are estimates for generating text with llama.cpp-style runtimes; real numbers usually land within about 20%.

Apps that support the M3 Ultra 256GB

Ollama LM Studio Jan GPT4All AnythingLLM llama.cpp MLX LM KoboldCpp Text Generation WebUI LocalAI