Can I run it?
Can I run MiMo V2.6 Distill Qwen 9B on Apple M3 Pro?
Runs
Runs fully in unified memory on your Apple M3 Pro at Q8_0, 8K context, about 8.4–11 tok/s. Weights 8.89 GB plus 0.27 GB of KV cache — 9.55 GB of 13.0 GB usable. Up to 64K context still fits.
Best quantQ8_0
Working context8K
Max that fits64K
Speed8.4–11 tok/sEstimate from memory bandwidth, not a benchmark. Method.
Weights8.89 GB
KV cache0.27 GB
Total9.55 GB
Usable13.0 GB
MiMo V2.6 Distill Qwen 9B details · Apple M3 Pro page · How this estimate is made
Run commands
llama.cpp
llama-server -hf bartowski/MiMo-V2.6-Distill-Qwen-9B-GGUF:Q8_0 -c 8192 -ngl 32
No matching name in the Ollama library snapshot.
LM Studio
lms get bartowski/MiMo-V2.6-Distill-Qwen-9B-GGUF # Then load quant Q8_0
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%.
- Q8_0 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 M3 Pro? — Tight fit, UD-IQ3_S, 6.6–8.9 tok/s (estimate)
- Can I run gemma 4 12b it on Apple M3 Pro? — Tight fit, UD-Q6_K_XL, 5.9–8.1 tok/s (estimate)
- Can I run Qwen3.5 9B on Apple M3 Pro? — Tight fit, UD-Q8_K_XL, 6.3–8.6 tok/s (estimate)
Updated 2026-10-24. Profile on this page is the device default.