Can I run it?
Can I run Qwen3.8 27B on Apple M4 Max (40-core GPU)?
Runs
Runs fully in unified memory on your Apple M4 Max (40-core GPU) at UD-Q8_K_L, 8K context, about 11–14 tok/s. Weights 26.1 GB plus 0.57 GB of KV cache — 27.3 GB of 36.0 GB usable. Up to 128K context still fits.
Best quantUD-Q8_K_L
Working context8K
Max that fits128K
Speed11–14 tok/s
Weights26.1 GB
KV cache0.57 GB
Total27.3 GB
Usable36.0 GB
Qwen3.8 27B details · Apple M4 Max (40-core GPU) page · How this estimate is made
Run commands
llama.cpp
llama-server -hf unsloth/Qwen3.8-27B-GGUF:UD-Q8_K_L -c 8192 -ngl 64
Ollama
ollama run qwen3.8
LM Studio
lms get unsloth/Qwen3.8-27B-GGUF # Then load quant UD-Q8_K_L
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_L 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 Max (40-core GPU)? — Tight fit, Q8_0, 89–122 tok/s
- Can I run Qwen3.8 35B A3B Distill on Apple M4 Max (40-core GPU)? — Runs, Q6_K, 114–155 tok/s
- Can I run Qwen3.5 35B A3B on Apple M4 Max (40-core GPU)? — Tight fit, Q8_0, 89–122 tok/s
Updated 2026-10-24. Profile on this page is the device default.