Mistral Medium 3.5 128B on RTX PRO 6000 Blackwell: VRAM, speed and fit
Mistral Medium 3.5 128B at 4-bit runs on the RTX PRO 6000 Blackwell with 52K of context at about 16 tokens a second.
Text generation · Chat · Ollama / LM Studio
Runs comfortably · on RTX PRO 6000 Blackwell · 4-bit (Q4_K_M) · Ollama / LM Studio · Chat
- GPU memory
- 91.1 GB
- of 96.0 GB
- Context
- 52K
- auto
- Speed
- 16 tok/s
- 13 when full
- First reply
- 2.1 s
- 2K prompt
Where the memory goes
- Model
- 72.1 GB
- Context
- 17.9 GB
- Overhead
- 1.1 GB
- OS
- 0.0 GB
- Free
- 4.9 GB
- Memory
- 91.1 GB of 96.0 GB
- Context
- 52K tokens · auto
- Speed
- 16 tok/s · 13 when full
- First reply
- 2.1 s for a 2K prompt
- Running cost
- $9.63/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 | 91.1 GB needed | Pass |
| Headroom | 5% free | 4.9 GB free (5%) | Pass |
| Context for chat | 16K or more | 52K | Pass |
| Writing speed | 15 tok/s or more | 16 tok/s | Pass |
| First reply | under 3 s, 2K prompt | 2.1 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
- 52K, auto
- Chats at once
- 1
- Use
- Chat
- Runs in
- Ollama / LM Studio
- Hardware
- RTX PRO 6000 Blackwell
- GPU can use
- 96.0 GB of 96.0 GB
Worth trying
- 8-bit cache: Room for 96K context
Running cost
- At home
- $9.63/mo
- 440 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 6000 AdaJust misses
- L40SJust misses
- 2× RTX 5090Runs
- 4× RTX 3090Runs
- Mac mini M4 16 GBToo big
- Mac mini M4 24 GBToo big
- Mac mini M4 32 GBToo big
- Mac mini M4 Pro 24 GBToo big
All machines: Mistral Medium 3.5 128B VRAM requirements. Everything that runs here: what can the RTX PRO 6000 Blackwell run?
Other models that run on RTX PRO 6000 Blackwell
Questions
Can Mistral Medium 3.5 128B run on RTX PRO 6000 Blackwell?
Mistral Medium 3.5 128B at 4-bit runs on the RTX PRO 6000 Blackwell with 52K of context at about 16 tokens a second.
Report VR-1U6B6AP, calculated Nov 22, 2026 from published specs, not benchmarked.