Rent a GPU

Can the Apple M3 Ultra (256GB) run gpt-oss 120B?

Apple M3 Ultra (256GB) × gpt-oss 120B8K context
YesRuns fully on the GPU
Memory at Q8_0125 GB of 192 GB
Weights 124.1 GBKV cache 0.3 GBRuntime 0.6 GB
QuantQ8_0Near-lossless
Speed~91tokens per second
Max context128Kthe model's full window
  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 M3 Ultra (256GB) can run gpt-oss 120B fully in unified memory at Q8_0 (near-lossless), using about 125 GB of the 192 GB available, at roughly 91 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 71.7 GB here). You have room for Q8_0, which is near-lossless: pick that GGUF in LM Studio or from Hugging Face.

New to this? Step-by-step setup for the Apple M3 Ultra (256GB)

Run it in the cloud

No Apple M3 Ultra (256GB)? 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 192 GB the Apple M3 Ultra (256GB) can use. macOS lets the GPU use about 192 GB of the 256 GB unified memory by default.

QuantQualityMemoryFits?Speed
FP16Full quality234.5 GBToo big—
Q8_0Near-lossless125 GBFits~91 tok/s
Q6_KExcellent96.7 GBFits~118 tok/s
Q5_K_MVery good84 GBFits~135 tok/s
Q4_K_MGood, most popular71.7 GBFits~159 tok/s
Q3_K_MNoticeably degraded58 GBFits~197 tok/s
Q2_KHeavily degraded44.7 GBFits~257 tok/s

Measured speed from real Apple M3 Ultra (256GB) owners

Tokens per second that people measured on their own Apple M3 Ultra (256GB), next to our estimate.

No one has measured gpt-oss 120B on the Apple M3 Ultra (256GB) yet. The speeds above are estimates. Run the benchmark and yours becomes the first real number on this page.

Have an Apple M3 Ultra (256GB)? Add your real speed

One command times gpt-oss 120B in your own Ollama, shows you exactly what it would send, and asks before sending anything. No sign-up, no personal data.

macOS and Linux

curl -fsSL https://gpufit.dev/bench.sh | sh -s -- gpt-oss:120b

Windows (PowerShell)

$env:GPUFIT_MODEL="gpt-oss:120b"; irm https://gpufit.dev/bench.ps1 | iex

How the benchmark works

GPUs that run gpt-oss 120B comfortably

Models that run well on the Apple M3 Ultra (256GB)

Frequently asked questions

Can Apple M3 Ultra (256GB) run gpt-oss 120B?

Yes. The Apple M3 Ultra (256GB) can run gpt-oss 120B fully in unified memory at Q8_0 (near-lossless), using about 125 GB of the 192 GB available, at roughly 91 tokens/second.

How much VRAM does gpt-oss 120B need?

About 71.7 GB at Q4_K_M with 8,192 tokens of context, and about 234.5 GB at full FP16 precision.

How fast is gpt-oss 120B on the Apple M3 Ultra (256GB)?

Roughly 91 tokens per second at Q8_0, estimated from the Apple M3 Ultra (256GB)'s 819 GB/s memory bandwidth.