Mistral Medium 3.5 128B on M3 Ultra 96 GB: VRAM, speed and fit
Mistral Medium 3.5 128B at 3-bit runs on the M3 Ultra 96 GB with 24K of context at about 8.1 tokens a second.
Text generation · Chat · Ollama / LM Studio
Runs comfortably · on M3 Ultra 96 GB · 3-bit (Q3_K_M) · Ollama / LM Studio · Chat
- GPU memory
- 91.3 GB
- of 96.0 GB
- Context
- 24K
- auto
- Speed
- 8.1 tok/s
- Reading speed
- First reply
- 24 s
- 2K prompt
Where the memory goes
- Model
- 58.1 GB
- Context
- 8.3 GB
- Overhead
- 896 MB
- OS
- 24.0 GB
- Free
- 4.7 GB
- Memory
- 91.3 GB of 96.0 GB
- Context
- 24K tokens · auto
- Speed
- 8.1 tok/s · reading speed
- First reply
- 24 s for a 2K prompt
- Running cost
- $3.55/mo at home · $122/mo on a cloud 4× RTX A4500
Validation: Not validated
| Check | Target | Result | Status |
|---|---|---|---|
| Fits in GPU memory | 72.0 GB usable | 67.3 GB needed | Pass |
| Headroom | 5% free | 4.7 GB free (7%) | Pass |
| Context for chat | 16K or more | 24K | Pass |
| Writing speed | 15 tok/s or more | 8.1 tok/s | Check |
| First reply | under 3 s, 2K prompt | 24 s | Fails |
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
- 3-bit (Q3_K_M)
- Context
- 24K, auto
- Chats at once
- 1
- Use
- Chat
- Runs in
- Ollama / LM Studio
- Hardware
- M3 Ultra 96 GB
- GPU can use
- 72.0 GB of 96.0 GB
Worth trying
- 8-bit cache: Room for 48K context
Running cost
- At home
- $3.55/mo
- 162 W at the wall
- Renting instead
- $122/mo
- 4× RTX A4500 at $1.00/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
- Mac mini M4 Pro 48 GBToo big
- Mac mini M4 Pro 64 GBJust misses
- M4 Max 128 GBRuns
- M5 Max 128 GBRuns
- M3 Ultra 256 GBRuns
- M3 Ultra 512 GBRuns
- M5 Ultra 512 GBRuns
- Ryzen AI Max+ 395 64 GBJust misses
All machines: Mistral Medium 3.5 128B VRAM requirements. Everything that runs here: what can the M3 Ultra 96 GB run?
Other models that run on M3 Ultra 96 GB
Questions
Can Mistral Medium 3.5 128B run on M3 Ultra 96 GB?
Mistral Medium 3.5 128B at 3-bit runs on the M3 Ultra 96 GB with 24K of context at about 8.1 tokens a second.
Report VR-0CC2J8K, calculated Nov 22, 2026 from published specs, not benchmarked.