Can the Apple M1 run gpt-oss 20B?
No. gpt-oss 20B needs about 16 GB and the Apple M1 has at most 16 GB of unified memory, of which about 11 GB is usable for models. The most capable model it fits is Qwen3 14B, at about 4 tok/s.
gpt-oss 20B needsAbout 16 GB
Apple M1 has8 or 16 GB unified memory
Bandwidth68 GB/s
Estimated speedDoesn't fit
By memory size
Each Apple M1 version
- 8 GB (about 5 GB usable)Too big
- 16 GB (about 11 GB usable)Too big
What runs gpt-oss 20B
These cards have the memory for it, nearest to the Apple M1 first. The cheapest build on our list that runs it well is the Used workstation + 2× Tesla P100, from $750 used, at about 130 tok/s.
How we estimate
Speed is roughly memory bandwidth divided by the weights read per token, calibrated on our own rack. Sizes are Ollama's default 4-bit downloads plus about 1.2 GB for context. Real results are usually within about a third. Measured it yourself? Send us the number.
Keep going