Can I run it?
Can I run Qwen3.8 2B Distill on Apple M4 Pro?
Runs great
Runs great fully in unified memory on your Apple M4 Pro at BF16, 8K context, about 38–51 tok/s. Weights 3.63 GB plus 0.10 GB of KV cache — 4.07 GB of 18.0 GB usable. Up to 256K context still fits.
Best quantBF16
Working context8K
Max that fits256K
Speed38–51 tok/sEstimate from memory bandwidth, not a benchmark. Method.
Weights3.63 GB
KV cache0.10 GB
Total4.07 GB
Usable18.0 GB
Qwen3.8 2B Distill details · Apple M4 Pro page · How this estimate is made
Run commands
llama.cpp
llama-server -hf empero-ai/Qwen3.8-2B-Distill-GGUF:BF16 -c 8192 -ngl 24
Ollama
ollama run qwen3.8
LM Studio
lms get empero-ai/Qwen3.8-2B-Distill-GGUF # Then load quant BF16
Assumptions
- Estimate from memory bandwidth, not a benchmark. Decode speed uses 55–75% of peak bandwidth.
- 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 M4 Pro? — Tight fit, UD-Q4_K_XL, 8.3–11 tok/s (estimate)
- Can I run gemma 4 12b it on Apple M4 Pro? — Runs, UD-Q8_K_XL, 8.9–12 tok/s (estimate)
- Can I run Qwen3.5 9B on Apple M4 Pro? — Tight fit, BF16, 8.3–11 tok/s (estimate)
Updated 2026-10-24. Profile on this page is the device default.