Devstral Small 2 24B on 4× RTX 3090: VRAM, speed and fit
Devstral Small 2 24B at FP8 runs on the 4× RTX 3090 with 384K of context at about 25 tokens a second.
Text generation · Chat · Ollama / LM Studio
Runs comfortably · on 4× RTX 3090 · FP8 · Ollama / LM Studio · Chat
- GPU memory
- 86.8 GB
- of 96.0 GB
- Context
- 384K
- auto
- Speed
- 25 tok/s
- 7.3 when full
- First reply
- 0.4 s
- 2K prompt
Where the memory goes
- Model
- 24.0 GB
- Context
- 60.0 GB
- Overhead
- 2.8 GB
- OS
- 0.0 GB
- Free
- 9.2 GB
- Memory
- 86.8 GB of 96.0 GB
- Context
- 384K tokens · auto
- Speed
- 25 tok/s · 7.3 when full
- First reply
- 0.4 s for a 2K prompt
- Running cost
- $20/mo at home · $131/mo on a cloud 4× RTX A5000
Validation: Validated
| Check | Target | Result | Status |
|---|---|---|---|
| Fits in GPU memory | 96.0 GB usable | 86.8 GB needed | Pass |
| Headroom | 5% free | 9.2 GB free (10%) | Pass |
| Context for chat | 16K or more | 384K | Pass |
| Writing speed | 15 tok/s or more | 25 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
- Devstral Small 2 24B
- Parameters
- 24B
- Precision
- FP8
- Context
- 384K, auto
- Chats at once
- 1
- Use
- Chat
- Runs in
- Ollama / LM Studio
- Hardware
- 4× RTX 3090
- GPU can use
- 96.0 GB of 96.0 GB
Running cost
- At home
- $20/mo
- 920 W at the wall
- Renting instead
- $131/mo
- 4× RTX A5000 at $1.08/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 devstral-small-2:24b- llama.cpp
llama-server -hf unsloth/Devstral-Small-2-24B-Instruct-2512-GGUF- vLLM
vllm serve mistralai/Devstral-Small-2-24B-Instruct-2512- MLX (Mac)
mlx_lm.chat --model mlx-community/Devstral-Small-2-24B-Instruct-2512-4bit
Devstral Small 2 24B on similar machines
- RTX PRO 5000 Blackwell 48 GBRuns
- RTX 6000 AdaRuns
- L40SRuns
- 2× RTX 5090Runs
- RTX PRO 6000 BlackwellRuns
- Mac mini M4 16 GBJust misses
- Mac mini M4 24 GBRuns
- Mac mini M4 32 GBRuns
All machines: Devstral Small 2 24B VRAM requirements. Everything that runs here: what can the 4× RTX 3090 run?
Other models that run on 4× RTX 3090
Questions
Can Devstral Small 2 24B run on 4× RTX 3090?
Devstral Small 2 24B at FP8 runs on the 4× RTX 3090 with 384K of context at about 25 tokens a second.
Report VR-1F6AS5D, calculated Nov 22, 2026 from published specs, not benchmarked.