Can I run it?
Can I run gpt oss 20b on Apple M4?
Won't fit
Won't fit on Apple M4. The smallest quant Q3_K_S is 10.7 GB before KV cache, and usable memory is 11.0 GB.
Best quantQ3_K_S
Working context—
Max that fits—
Speed—Estimate from memory bandwidth, not a benchmark. Method.
Weights10.7 GB
KV cache0.00 GB
Total0.00 GB
Usable11.0 GB
gpt oss 20b details · Apple M4 page · How this estimate is made
Run commands
llama.cpp
llama-server -hf unsloth/gpt-oss-20b-GGUF:Q3_K_S -c 2048 -ngl 0
No matching name in the Ollama library snapshot.
LM Studio
lms get unsloth/gpt-oss-20b-GGUF # Then load quant Q3_K_S
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%.
- No display reserve on this device.
- Usable memory for this profile is 11.0 GB.
Models that fit this machine more comfortably
- Can I run Qwen3.6 35B A3B on Apple M4? — Heavily degraded, UD-IQ2_XXS, 15–20 tok/s (estimate)
- Can I run Qwen3.5 35B A3B on Apple M4? — Heavily degraded, UD-IQ2_XXS, 15–20 tok/s (estimate)
- Can I run Qwen2.5 32B Instruct on Apple M4? — Heavily degraded, IQ2_XXS, 6.5–8.9 tok/s (estimate)
Updated 2026-10-24. Profile on this page is the device default.