Can I run it?

Can I run Qwen3.8 2B Distill on Apple M5 Max (40-core GPU)?

Runs great

Runs great fully in unified memory on your Apple M5 Max (40-core GPU) at BF16, 8K context, about 84–115 tok/s. Weights 3.63 GB plus 0.10 GB of KV cache — 4.07 GB of 36.0 GB usable. Up to 256K context still fits.

Qwen3.8 2B Distill details · Apple M5 Max (40-core GPU) page · How this estimate is made

Run commands

llama-server -hf empero-ai/Qwen3.8-2B-Distill-GGUF:BF16 -c 8192 -ngl 24

ollama run qwen3.8

lms get empero-ai/Qwen3.8-2B-Distill-GGUF
# Then load quant BF16

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%.
• BF16 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 M5 Max (40-core GPU)? — Runs, UD-Q8_K_L, 12–16 tok/s
• Can I run gemma 4 12b it on Apple M5 Max (40-core GPU)? — Runs, BF16, 12–17 tok/s
• Can I run Qwen3.5 9B on Apple M5 Max (40-core GPU)? — Runs great, BF16, 19–25 tok/s

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