Can I run it?
Can I run Qwen3 30B A3B Instruct 2507 on Apple M4?
Tight fit
Tight fit fully in unified memory on your Apple M4 at UD-IQ2_XXS, 8K context, about 36–49 tok/s. Weights 9.63 GB plus 0.75 GB of KV cache — 10.8 GB of 11.0 GB usable.
Best quantUD-IQ2_XXS
Working context8K
Max that fits8K
Speed36–49 tok/s
Weights9.63 GB
KV cache0.75 GB
Total10.8 GB
Usable11.0 GB
Qwen3 30B A3B Instruct 2507 details · Apple M4 page · How this estimate is made
Run commands
llama.cpp
llama-server -hf unsloth/Qwen3-30B-A3B-Instruct-2507-GGUF:UD-IQ2_XXS -c 8192 -ngl 48
Ollama
ollama run qwen3
LM Studio
lms get unsloth/Qwen3-30B-A3B-Instruct-2507-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 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
- Can I run Qwen2.5 32B Instruct on Apple M4? — Tight fit, IQ2_XXS, 6.5–8.9 tok/s
Updated 2026-10-24. Profile on this page is the device default.