gpt-oss 20B on 2× RTX 3090: VRAM, speed and fit
gpt-oss 20B at MXFP4 runs on the 2× RTX 3090 with 128K of context at about 187 tokens a second.
Text generation · Chat · Ollama / LM Studio
Runs comfortably · on 2× RTX 3090 · MXFP4 · Ollama / LM Studio · Chat
- GPU memory
- 15.9 GB
- of 48.0 GB
- Context
- 128K
- auto
- Speed
- 187 tok/s
- 97 when full
- First reply
- 0.3 s
- 2K prompt
Where the memory goes
- Model
- 11.3 GB
- Context
- 3.0 GB
- Overhead
- 1.6 GB
- OS
- 0.0 GB
- Free
- 32.1 GB
- Memory
- 15.9 GB of 48.0 GB
- Context
- 128K tokens · auto
- Speed
- 187 tok/s · 97 when full
- First reply
- 0.3 s for a 2K prompt
- Running cost
- $11/mo at home · $29/mo on a cloud RTX 2000 Ada
Validation: Validated
| Check | Target | Result | Status |
|---|---|---|---|
| Fits in GPU memory | 48.0 GB usable | 15.9 GB needed | Pass |
| Headroom | 5% free | 32.1 GB free (67%) | Pass |
| Context for chat | 16K or more | 128K | Pass |
| Writing speed | 15 tok/s or more | 187 tok/s | Pass |
| First reply | under 3 s, 2K prompt | 0.3 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 20B
- Parameters
- 20.9B, 3.6B active
- Precision
- MXFP4
- Context
- 128K, auto
- Chats at once
- 1
- Use
- Chat
- Runs in
- Ollama / LM Studio
- Hardware
- 2× RTX 3090
- GPU can use
- 48.0 GB of 48.0 GB
Running cost
- At home
- $11/mo
- 500 W at the wall
- Renting instead
- $29/mo
- RTX 2000 Ada at $0.24/h
4 h a day, power at $0.18 per kWh, cloud at RunPod on-demand prices as of Nov 22, 2026.
How to run it
- Ollama
ollama run gpt-oss:20b- llama.cpp
llama-server -hf unsloth/gpt-oss-20b-GGUF- vLLM
vllm serve openai/gpt-oss-20b- MLX (Mac)
mlx_lm.chat --model mlx-community/gpt-oss-20b-MXFP4-Q4- Model card
- huggingface.co/openai/gpt-oss-20b
gpt-oss 20B on similar machines
- RTX 3090Runs
- RTX 4090Runs
- Radeon AI PRO R9700Runs
- RTX 5090Runs
- 2× RTX 4090Runs
- RTX PRO 5000 Blackwell 48 GBRuns
- RTX 6000 AdaRuns
- L40SRuns
All machines: gpt-oss 20B VRAM requirements. Everything that runs here: what can the 2× RTX 3090 run?
Other models that run on 2× RTX 3090
Questions
Can gpt-oss 20B run on 2× RTX 3090?
gpt-oss 20B at MXFP4 runs on the 2× RTX 3090 with 128K of context at about 187 tokens a second.
Report VR-1MR9UYI, calculated Nov 22, 2026 from published specs, not benchmarked.