Can I run it?

Can I run gemma 4 31B it on Apple M3 Pro?

Runs

Runs fully in unified memory on your Apple M3 Pro at UD-IQ2_XXS, 8K context, about 5.0–6.8 tok/s. Weights 7.95 GB plus 2.03 GB of KV cache — 10.4 GB of 13.0 GB usable. Up to 16K context still fits.

gemma 4 31B it details · Apple M3 Pro page · How this estimate is made

Run commands

llama-server -hf unsloth/gemma-4-31B-it-GGUF:UD-IQ2_XXS -c 8192 -ngl 60

ollama run gemma

lms get unsloth/gemma-4-31B-it-GGUF
# Then load quant UD-IQ2_XXS

Assumptions

• Estimate, not a benchmark. Decode speed uses a memory-bandwidth model at 55–75% of peak.
• KV cache is FP16. Engine overhead assumes llama.cpp (0.3 GB + 1% of the weights). Ollama is closer to 0.9 GB + 3%, LM Studio closer to 1 GB + 3%.
• UD-IQ2_XXS size is the real GGUF file size from Hugging Face.
• Unified memory uses 75% for the GPU by default, and always leaves about 5 GB for the OS.
• Speed is quoted at 8K context, not at the maximum context that still fits.

Larger models that also fit

• Can I run Qwen3.6 35B A3B on Apple M3 Pro? — Tight fit, UD-Q2_K_XL, 67–91 tok/s
• Can I run Qwen3.5 35B A3B on Apple M3 Pro? — Tight fit, UD-IQ3_XXS, 68–93 tok/s
• Can I run Qwen2.5 32B Instruct on Apple M3 Pro? — Tight fit, IQ2_S, 6.6–9.0 tok/s

Updated 2026-10-24. Profile on this page is the device default.