Can I run it?
Can I run Qwen3 Coder 30B A3B Instruct on Apple M5 Max (40-core GPU)?
Tight fit
Tight fit fully in unified memory on your Apple M5 Max (40-core GPU) at UD-Q8_K_XL, 8K context, about 78–106 tok/s. Weights 33.5 GB plus 0.75 GB of KV cache — 34.9 GB of 36.0 GB usable.
Best quantUD-Q8_K_XL
Working context8K
Max that fits8K
Speed78–106 tok/s
Weights33.5 GB
KV cache0.75 GB
Total34.9 GB
Usable36.0 GB
Qwen3 Coder 30B A3B Instruct details · Apple M5 Max (40-core GPU) page · How this estimate is made
Run commands
llama.cpp
llama-server -hf unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF:UD-Q8_K_XL -c 8192 -ngl 48
Ollama
ollama run qwen3
LM Studio
lms get unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF # Then load quant UD-Q8_K_XL
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-Q8_K_XL 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 Cyber Tiel Coder 35B A3B GGUF MTP on Apple M5 Max (40-core GPU)? — Runs, Q6_K, 129–175 tok/s
- Can I run Tiel Coder 35B A3B on Apple M5 Max (40-core GPU)? — Runs, UD-Q6_K_XL, 115–157 tok/s
- Can I run Kwaipilot KAT Coder V2.5 Dev on Apple M5 Max (40-core GPU)? — Tight fit, Q8_0, 49–67 tok/s
Updated 2026-10-24. Profile on this page is the device default.