Pixtral 12B on 2× RTX 3090: VRAM, speed and fit
Pixtral 12B at 8-bit runs on the 2× RTX 3090 with 200K of context at about 48 tokens a second.
Text generation · Chat · Ollama / LM Studio
Runs comfortably · on 2× RTX 3090 · 8-bit (Q8_0) · Ollama / LM Studio · Chat
- GPU memory
- 45.3 GB
- of 48.0 GB
- Context
- 200K
- auto
- Speed
- 48 tok/s
- 14 when full
- First reply
- 0.4 s
- 2K prompt
Where the memory goes
- Model
- 12.5 GB
- Context
- 31.3 GB
- Overhead
- 1.5 GB
- OS
- 0.0 GB
- Free
- 2.7 GB
- Memory
- 45.3 GB of 48.0 GB
- Context
- 200K tokens · auto
- Speed
- 48 tok/s · 14 when full
- First reply
- 0.4 s for a 2K prompt
- Running cost
- $11/mo at home · $66/mo on a cloud 2× RTX A5000
Validation: Validated
| Check | Target | Result | Status |
|---|---|---|---|
| Fits in GPU memory | 48.0 GB usable | 45.3 GB needed | Pass |
| Headroom | 5% free | 2.7 GB free (6%) | Pass |
| Context for chat | 16K or more | 200K | Pass |
| Writing speed | 15 tok/s or more | 48 tok/s | Pass |
| First reply | under 3 s, 2K prompt | 0.4 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
- Pixtral 12B
- Parameters
- 12.7B
- Precision
- 8-bit (Q8_0)
- Context
- 200K, 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
- $66/mo
- 2× RTX A5000 at $0.54/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
- llama.cpp
llama-server -hf ggml-org/pixtral-12b-GGUF- vLLM
vllm serve mistral-experimental/pixtral-12b
Pixtral 12B 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: Pixtral 12B VRAM requirements. Everything that runs here: what can the 2× RTX 3090 run?
Other models that run on 2× RTX 3090
Questions
Can Pixtral 12B run on 2× RTX 3090?
Pixtral 12B at 8-bit runs on the 2× RTX 3090 with 200K of context at about 48 tokens a second.
Report VR-0HQWW1Y, calculated Nov 22, 2026 from published specs, not benchmarked.