Can I run it?

Can I run Qwen3.8 35B A3B Distill on Apple M4 Max (40-core GPU)?

Runs

Runs fully in unified memory on your Apple M4 Max (40-core GPU) at Q6_K, 8K context, about 114–155 tok/s. Weights 27.2 GB plus 0.19 GB of KV cache — 28.0 GB of 36.0 GB usable. Up to 256K context still fits.

Qwen3.8 35B A3B Distill details · Apple M4 Max (40-core GPU) page · How this estimate is made

Run commands

llama-server -hf empero-ai/Qwen3.8-35B-A3B-Distill-GGUF:Q6_K -c 8192 -ngl 40

ollama run qwen3.8

lms get empero-ai/Qwen3.8-35B-A3B-Distill-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 Cyber Tiel Coder 35B A3B GGUF MTP on Apple M4 Max (40-core GPU)? — Runs, Q6_K, 114–156 tok/s
• Can I run Qwen3 Next 80B A3B Instruct on Apple M4 Max (40-core GPU)? — Tight fit, UD-Q3_K_XL, 140–191 tok/s
• Can I run Qwen2.5 72B Instruct on Apple M4 Max (40-core GPU)? — Tight fit, IQ3_M, 8.2–11 tok/s

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