Can Apple M5 Ultra run gpt-oss 120B?
Last updated:
Yes. Measured 95 tok/s generation (Ollama 0.40.13 (llamacpp runner), MXFP4 (Ollama gpt-oss:120b, 65 GB); source).
Every measured result for gpt-oss 120B on Apple M5 Ultra
| Build | Quant / setup | Engine | tok/s | |
|---|---|---|---|---|
| Mac Studio M5 Ultra 96 GB (64-core GPU): gpt-oss 120B at 95 tok/s, 2,588 tok/s prefill at 15K (Ollama) | MXFP4 (Ollama gpt-oss:120b, 65 GB) | Ollama 0.40.13 (llamacpp runner) | 95 | source |
Memory: Apple M5 Ultra has 96 GB. gpt-oss 120B weights are about 65 GB in its native format (OpenAI model card: 117B total, 5.1B active). Arithmetic, not a measurement; long contexts need more. Check other quants in the VRAM calculator.
Speeds are decode (generation) tokens/sec as reported by each source; quant, engine and context differ, so small gaps are noise.
All measured speeds for gpt-oss 120B: best home rig for gpt-oss 120B.
gpt-oss 120B on other hardware: Apple M2 Ultra · DGX Spark (GB10) · RTX 3090 · RTX Pro 6000 (Blackwell, 96 GB) · Strix Halo (Radeon 8060S)
Other models measured on Apple M5 Ultra: Mistral Medium 3.5 128B · Qwen3.6 35B-A3B · Qwen3.8 27B · Qwen3.8 Flash-Next
Not enough VRAM? Rent before you buy. Run gpt-oss 120B on a bigger GPU on a rented 24–96 GB cloud GPU by the hour and see the real speed before spending €1,000+. Try it on Runpod
Referral link: if you sign up with Google and add $10, Runpod gives you and RigBase bonus credit (terms). It never affects our data.
Referral link: if you sign up with Google and add $10, Runpod gives you and RigBase bonus credit (terms). It never affects our data.