Can I run it?
Can I run gpt oss 20b on Apple M3 Pro?
Tight fit
Tight fit fully in unified memory on your Apple M3 Pro at Q5_K_M, 8K context, about 13–18 tok/s. Weights 10.9 GB plus 0.19 GB of KV cache — 11.5 GB of 13.0 GB usable. Up to 32K context still fits.
Best quantQ5_K_M
Working context8K
Max that fits32K
Speed13–18 tok/sEstimate from memory bandwidth, not a benchmark. Method.
Weights10.9 GB
KV cache0.19 GB
Total11.5 GB
Usable13.0 GB
gpt oss 20b details · Apple M3 Pro page · How this estimate is made
Run commands
llama.cpp
llama-server -hf unsloth/gpt-oss-20b-GGUF:Q5_K_M -c 8192 -ngl 24
No matching name in the Ollama library snapshot.
LM Studio
lms get unsloth/gpt-oss-20b-GGUF # Then load quant Q5_K_M
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%.
- Q5_K_M 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 Qwen3.6 35B A3B on Apple M3 Pro? — Tight fit, UD-Q2_K_XL, 16–22 tok/s (estimate)
- Can I run gemma 4 26B A4B it on Apple M3 Pro? — Tight fit, Q3_K_M, 13–18 tok/s (estimate)
Updated 2026-10-24. Profile on this page is the device default.