gpt-oss 120B on H100 SXM: VRAM, speed and fit
gpt-oss 120B at MXFP4 runs on the H100 SXM with 128K of context at about 269 tokens a second.
Text generation · Chat · Ollama / LM Studio
Runs comfortably · on H100 SXM · MXFP4 · Ollama / LM Studio · Chat
- GPU memory
- 64.5 GB
- of 80.0 GB
- Context
- 128K
- auto
- Speed
- 269 tok/s
- 173 when full
- First reply
- 0.2 s
- 2K prompt
Where the memory goes
- Model
- 59.0 GB
- Context
- 4.5 GB
- Overhead
- 944 MB
- OS
- 0.0 GB
- Free
- 15.5 GB
- Memory
- 64.5 GB of 80.0 GB
- Context
- 128K tokens · auto
- Speed
- 269 tok/s · 173 when full
- First reply
- 0.2 s for a 2K prompt
- Running cost
- $11/mo at home · $122/mo on a cloud 4× RTX A4500
Validation: Validated
| Check | Target | Result | Status |
|---|---|---|---|
| Fits in GPU memory | 80.0 GB usable | 64.5 GB needed | Pass |
| Headroom | 5% free | 15.5 GB free (19%) | Pass |
| Context for chat | 16K or more | 128K | Pass |
| Writing speed | 15 tok/s or more | 269 tok/s | Pass |
| First reply | under 3 s, 2K prompt | 0.2 s | Pass |
Targets: a reply you can read along with, a first reply the use case tolerates, and 5% of memory left free. Calculated from published specs, not benchmarked.
The setup
- Model
- gpt-oss 120B
- Parameters
- 117B, 5.1B active
- Precision
- MXFP4
- Context
- 128K, auto
- Chats at once
- 1
- Use
- Chat
- Runs in
- Ollama / LM Studio
- Hardware
- H100 SXM
- GPU can use
- 80.0 GB of 80.0 GB
Running cost
- At home
- $11/mo
- 500 W at the wall
- Renting instead
- $122/mo
- 4× RTX A4500 at $1.00/h
4 h a day, power at $0.18 per kWh, cloud at RunPod on-demand prices as of Nov 21, 2026.
How to run it
- Ollama
ollama run gpt-oss:120b- llama.cpp
llama-server -hf unsloth/gpt-oss-120b-GGUF- vLLM
vllm serve openai/gpt-oss-120b- MLX (Mac)
mlx_lm.chat --model mlx-community/gpt-oss-120b-MXFP4-Q4- Model card
- huggingface.co/openai/gpt-oss-120b
gpt-oss 120B on similar machines
- 2× RTX PRO 6000 BlackwellRuns
- 4× RTX PRO 6000 BlackwellRuns
- 8× RTX PRO 6000 BlackwellRuns
- A100 80 GB SXMRuns
- 4× H200 NVLRuns
- 8× H200 NVLRuns
All machines: gpt-oss 120B VRAM requirements. Everything that runs here: what can the H100 SXM run?
Other models that run on H100 SXM
Questions
Can gpt-oss 120B run on H100 SXM?
gpt-oss 120B at MXFP4 runs on the H100 SXM with 128K of context at about 269 tokens a second.
Report VR-1PN9OM4, calculated Nov 22, 2026 from published specs, not benchmarked.