Mistral Medium 3.5 128B on 4× RTX 3090: VRAM, speed and fit
Mistral Medium 3.5 128B at 4-bit runs on the 4× RTX 3090 with 44K of context at about 8.4 tokens a second.
Text generation · Chat · Ollama / LM Studio
Runs comfortably · on 4× RTX 3090 · 4-bit (Q4_K_M) · Ollama / LM Studio · Chat
- GPU memory
- 90.6 GB
- of 96.0 GB
- Context
- 44K
- auto
- Speed
- 8.4 tok/s
- 6.9 when full
- First reply
- 2.4 s
- 2K prompt
Where the memory goes
- Model
- 72.1 GB
- Context
- 15.1 GB
- Overhead
- 3.4 GB
- OS
- 0.0 GB
- Free
- 5.4 GB
- Memory
- 90.6 GB of 96.0 GB
- Context
- 44K tokens · auto
- Speed
- 8.4 tok/s · 6.9 when full
- First reply
- 2.4 s for a 2K prompt
- Running cost
- $20/mo at home · $131/mo on a cloud 4× RTX A5000
Validation: Validated with conditions
| Check | Target | Result | Status |
|---|---|---|---|
| Fits in GPU memory | 96.0 GB usable | 90.6 GB needed | Pass |
| Headroom | 5% free | 5.4 GB free (6%) | Pass |
| Context for chat | 16K or more | 44K | Pass |
| Writing speed | 15 tok/s or more | 8.4 tok/s | Check |
| First reply | under 3 s, 2K prompt | 2.4 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
- Mistral Medium 3.5 128B
- Parameters
- 128B
- Precision
- 4-bit (Q4_K_M)
- Context
- 44K, 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
Worth trying
- 8-bit cache: Room for 80K context
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 mistral-medium-3.5:128b- llama.cpp
llama-server -hf unsloth/Mistral-Medium-3.5-128B-GGUF- vLLM
vllm serve mistralai/Mistral-Medium-3.5-128B- MLX (Mac)
mlx_lm.chat --model mlx-community/Mistral-Medium-3.5-128B-4bit
Mistral Medium 3.5 128B on similar machines
- RTX PRO 5000 Blackwell 48 GBJust misses
- RTX 6000 AdaJust misses
- L40SJust misses
- 2× RTX 5090Runs
- RTX PRO 6000 BlackwellRuns
- Mac mini M4 16 GBToo big
- Mac mini M4 24 GBToo big
- Mac mini M4 32 GBToo big
All machines: Mistral Medium 3.5 128B VRAM requirements. Everything that runs here: what can the 4× RTX 3090 run?
Other models that run on 4× RTX 3090
Questions
Can Mistral Medium 3.5 128B run on 4× RTX 3090?
Mistral Medium 3.5 128B at 4-bit runs on the 4× RTX 3090 with 44K of context at about 8.4 tokens a second.
Report VR-0SBGQDM, calculated Nov 22, 2026 from published specs, not benchmarked.