Can I run it?
Can I run gemma 4 12b it on Apple M4?
Tight fit
Tight fit fully in unified memory on your Apple M4 at Q6_K, 8K context, about 5.1–6.9 tok/s. Weights 9.11 GB plus 0.81 GB of KV cache — 10.3 GB of 11.0 GB usable.
Best quantQ6_K
Working context8K
Max that fits8K
Speed5.1–6.9 tok/s
Weights9.11 GB
KV cache0.81 GB
Total10.3 GB
Usable11.0 GB
gemma 4 12b it details · Apple M4 page · How this estimate is made
Run commands
llama.cpp
llama-server -hf unsloth/gemma-4-12b-it-GGUF:Q6_K -c 8192 -ngl 48
Ollama
ollama run gemma
LM Studio
lms get unsloth/gemma-4-12b-it-GGUF # Then load quant Q6_K
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%.
- Q6_K 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 Qwen3.8 27B on Apple M4? — Tight fit, UD-Q2_K_XL, 6.4–8.7 tok/s
- Can I run Qwen3.6 35B A3B on Apple M4? — Tight fit, UD-IQ2_XXS, 60–82 tok/s
- Can I run Qwen3.5 35B A3B on Apple M4? — Tight fit, UD-IQ2_XXS, 61–83 tok/s
Updated 2026-10-24. Profile on this page is the device default.