Rent a GPU

Can the Apple M4 Max (128GB) run gpt-oss 20B?

Apple M4 Max (128GB) × gpt-oss 20B8K context
YesRuns fully on the GPU
Memory at FP1642.8 GB of 96 GB
Weights 41.8 GBKV cache 0.4 GBRuntime 0.6 GB
QuantFP16Full quality
Memory42.8 GBof 96 GB usable
Speed~45tokens 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 20B fully in unified memory at FP16 (full quality), using about 42.8 GB of the 96 GB available, at roughly 45 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 FP16, which is full quality: pick that GGUF in LM Studio or from Hugging Face.

Run it in the cloud

No Apple M4 Max (128GB)? 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 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 quality42.8 GBFits~45 tok/s
Q8_0Near-lossless23.2 GBFits~86 tok/s
Q6_KExcellent18.1 GBFits~111 tok/s
Q5_K_MVery good15.9 GBFits~128 tok/s
Q4_K_MGood, most popular13.7 GBFits~150 tok/s
Q3_K_MNoticeably degraded11.2 GBFits~186 tok/s
Q2_KHeavily degraded8.8 GBFits~243 tok/s

GPUs that run gpt-oss 20B comfortably

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

Frequently asked questions

Can Apple M4 Max (128GB) run gpt-oss 20B?

Yes. The Apple M4 Max (128GB) can run gpt-oss 20B fully in unified memory at FP16 (full quality), using about 42.8 GB of the 96 GB available, at roughly 45 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 M4 Max (128GB)?

Roughly 45 tokens per second at FP16, estimated from the Apple M4 Max (128GB)'s 546 GB/s memory bandwidth.