Rent a GPU

Can the Apple M2 Pro (32GB) run gpt-oss 20B?

Apple M2 Pro (32GB) × gpt-oss 20B8K context
YesRuns fully on the GPU
Memory at Q6_K18.1 GB of 21.4 GB
Weights 17.1 GBKV cache 0.4 GBRuntime 0.6 GB
QuantQ6_KExcellent
Memory18.1 GBof 21.4 GB usable
Speed~41tokens per second
  1. FP16
  2. Q8_0
  3. Q6_K
  4. Q5_K_M
  5. Q4_K_M
  6. Q3_K_M
  7. Q2_K

Yes. The Apple M2 Pro (32GB) can run gpt-oss 20B fully in unified memory at Q6_K (excellent), using about 18.1 GB of the 21.4 GB available, at roughly 41 tokens/second.

Try other context lengths

Run it with Ollama

With Ollama installed, one command downloads and starts gpt-oss 20B:

ollama run gpt-oss:20b

Ollama's default download is Q4_K_M (about 13.7 GB here). You have room for Q6_K, which is excellent: pick that GGUF in LM Studio or from Hugging Face.

Run it in the cloud

No Apple M2 Pro (32GB)? Run gpt-oss 20B in the cloud.

Rent a cloud GPU by the hour. No upfront cost, stop any time.

Rent a GPU on RunPodRent a GPU on Vast.ai

Memory needed by quantization

At 8,192 tokens of context. The black line marks the 21.4 GB the Apple M2 Pro (32GB) can use. macOS lets the GPU use about 21.4 GB of the 32 GB unified memory by default.

QuantQualityMemoryFits?Speed
FP16Full quality42.8 GBToo big—
Q8_0Near-lossless23.2 GBToo big—
Q6_KExcellent18.1 GBFits~41 tok/s
Q5_K_MVery good15.9 GBFits~47 tok/s
Q4_K_MGood, most popular13.7 GBFits~55 tok/s
Q3_K_MNoticeably degraded11.2 GBFits~68 tok/s
Q2_KHeavily degraded8.8 GBFits~89 tok/s

GPUs that run gpt-oss 20B comfortably

Models that run well on the Apple M2 Pro (32GB)

Frequently asked questions

Can Apple M2 Pro (32GB) run gpt-oss 20B?

Yes. The Apple M2 Pro (32GB) can run gpt-oss 20B fully in unified memory at Q6_K (excellent), using about 18.1 GB of the 21.4 GB available, at roughly 41 tokens/second.

How much VRAM does gpt-oss 20B need?

About 13.7 GB at Q4_K_M with 8,192 tokens of context, and about 42.8 GB at full FP16 precision.

How fast is gpt-oss 20B on the Apple M2 Pro (32GB)?

Roughly 41 tokens per second at Q6_K, estimated from the Apple M2 Pro (32GB)'s 200 GB/s memory bandwidth.