Rent a GPU

Can the Apple M4 Max (128GB) run gpt-oss 120B?

Apple M4 Max (128GB) × gpt-oss 120B8K context
YesRuns fully on the GPU
Memory at Q5_K_M84.3 GB of 96 GB
Weights 83.1 GBKV cache 0.6 GBRuntime 0.6 GB
QuantQ5_K_MVery good
Memory84.3 GBof 96 GB usable
Speed~90tokens 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 M4 Max (128GB) can run gpt-oss 120B fully in unified memory at Q5_K_M (very good), using about 84.3 GB of the 96 GB available, at roughly 90 tokens/second.

Try other context lengths

Run it with Ollama

With Ollama installed, one command downloads and starts gpt-oss 120B:

ollama run gpt-oss:120b

Ollama's default download is Q4_K_M (about 72 GB here). You have room for Q5_K_M, which is very good: pick that GGUF in LM Studio or from Hugging Face.

Run it in the cloud

No Apple M4 Max (128GB)? Run gpt-oss 120B 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 96 GB the Apple M4 Max (128GB) can use. macOS lets the GPU use about 96 GB of the 128 GB unified memory by default.

QuantQualityMemoryFits?Speed
FP16Full quality234.8 GBToo big—
Q8_0Near-lossless125.3 GBToo big—
Q6_KExcellent97 GBToo big—
Q5_K_MVery good84.3 GBFits~90 tok/s
Q4_K_MGood, most popular72 GBFits~106 tok/s
Q3_K_MNoticeably degraded58.3 GBFits~131 tok/s
Q2_KHeavily degraded45 GBFits~171 tok/s

GPUs that run gpt-oss 120B comfortably

Models that run well on the Apple M4 Max (128GB)

Frequently asked questions

Can Apple M4 Max (128GB) run gpt-oss 120B?

Yes. The Apple M4 Max (128GB) can run gpt-oss 120B fully in unified memory at Q5_K_M (very good), using about 84.3 GB of the 96 GB available, at roughly 90 tokens/second.

How much VRAM does gpt-oss 120B need?

About 72 GB at Q4_K_M with 8,192 tokens of context, and about 234.8 GB at full FP16 precision.

How fast is gpt-oss 120B on the Apple M4 Max (128GB)?

Roughly 90 tokens per second at Q5_K_M, estimated from the Apple M4 Max (128GB)'s 546 GB/s memory bandwidth.