Mistral Medium 3.5 128B on 2× RTX 5090: VRAM, speed and fit
Mistral Medium 3.5 128B at 2-bit runs on the 2× RTX 5090 with 40K of context at about 25 tokens a second.
Text generation · Chat · Ollama / LM Studio
Runs comfortably · on 2× RTX 5090 · 2-bit (Q2_K) · Ollama / LM Studio · Chat
- GPU memory
- 60.2 GB
- of 64.0 GB
- Context
- 40K
- auto
- Speed
- 25 tok/s
- 19 when full
- First reply
- 1.5 s
- 2K prompt
Where the memory goes
- Model
- 44.6 GB
- Context
- 13.8 GB
- Overhead
- 1.8 GB
- OS
- 0.0 GB
- Free
- 3.8 GB
- Memory
- 60.2 GB of 64.0 GB
- Context
- 40K tokens · auto
- Speed
- 25 tok/s · 19 when full
- First reply
- 1.5 s for a 2K prompt
- Running cost
- $17/mo at home · $117/mo on a cloud 4× RTX 2000 Ada
Validation: Validated
| Check | Target | Result | Status |
|---|---|---|---|
| Fits in GPU memory | 64.0 GB usable | 60.2 GB needed | Pass |
| Headroom | 5% free | 3.8 GB free (6%) | Pass |
| Context for chat | 16K or more | 40K | Pass |
| Writing speed | 15 tok/s or more | 25 tok/s | Pass |
| First reply | under 3 s, 2K prompt | 1.5 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
- 2-bit (Q2_K)
- Context
- 40K, auto
- Chats at once
- 1
- Use
- Chat
- Runs in
- Ollama / LM Studio
- Hardware
- 2× RTX 5090
- GPU can use
- 64.0 GB of 64.0 GB
Worth trying
- 8-bit cache: Room for 72K context
Running cost
- At home
- $17/mo
- 770 W at the wall
- Renting instead
- $117/mo
- 4× RTX 2000 Ada at $0.96/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
- 2× RTX 4090Just misses
- RTX PRO 5000 Blackwell 48 GBJust misses
- RTX 6000 AdaJust misses
- L40SJust misses
- 4× RTX 3090Runs
- RTX PRO 6000 BlackwellRuns
- Mac mini M4 16 GBToo big
- Mac mini M4 24 GBToo big
All machines: Mistral Medium 3.5 128B VRAM requirements. Everything that runs here: what can the 2× RTX 5090 run?
Other models that run on 2× RTX 5090
Questions
Can Mistral Medium 3.5 128B run on 2× RTX 5090?
Mistral Medium 3.5 128B at 2-bit runs on the 2× RTX 5090 with 40K of context at about 25 tokens a second.
Report VR-1M2GO26, calculated Nov 22, 2026 from published specs, not benchmarked.