Mistral Small 4 119B on M5 Ultra 512 GB: VRAM, speed and fit
Mistral Small 4 119B at FP8 runs on the M5 Ultra 512 GB with 256K of context at about 74 tokens a second.
Text generation · Chat · Ollama / LM Studio
Runs comfortably · on M5 Ultra 512 GB · FP8 · Ollama / LM Studio · Chat
- GPU memory
- 247 GB
- of 512 GB
- Context
- 256K
- auto
- Speed
- 74 tok/s
- 47 when full
- First reply
- 1.1 s
- 2K prompt
Where the memory goes
- Model
- 113 GB
- Context
- 5.6 GB
- Overhead
- 640 MB
- OS
- 128 GB
- Free
- 265 GB
- Memory
- 247 GB of 512 GB
- Context
- 256K tokens · auto
- Speed
- 74 tok/s · 47 when full
- First reply
- 1.1 s for a 2K prompt
- Running cost
- $5.06/mo at home · $287/mo on a cloud 4× A40
Validation: Validated
| Check | Target | Result | Status |
|---|---|---|---|
| Fits in GPU memory | 384 GB usable | 119 GB needed | Pass |
| Headroom | 5% free | 265 GB free (69%) | Pass |
| Context for chat | 16K or more | 256K | Pass |
| Writing speed | 15 tok/s or more | 74 tok/s | Pass |
| First reply | under 3 s, 2K prompt | 1.1 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 Small 4 119B
- Parameters
- 119B, 6.5B active
- Precision
- FP8
- Context
- 256K, auto
- Chats at once
- 1
- Use
- Chat
- Runs in
- Ollama / LM Studio
- Hardware
- M5 Ultra 512 GB
- GPU can use
- 384 GB of 512 GB
Running cost
- At home
- $5.06/mo
- 231 W at the wall
- Renting instead
- $287/mo
- 4× A40 at $2.36/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
- llama.cpp
llama-server -hf unsloth/Mistral-Small-4-119B-2603-GGUF- vLLM
vllm serve mistralai/Mistral-Small-4-119B-2603- MLX (Mac)
mlx_lm.chat --model mlx-community/Mistral-Small-4-119B-2603-4bit
Mistral Small 4 119B on similar machines
- M5 Max 128 GBRuns
- M3 Ultra 96 GBRuns
- M3 Ultra 256 GBRuns
- M3 Ultra 512 GBRuns
- Ryzen AI Max+ 395 64 GBRuns
- Ryzen AI Max+ 395 128 GBRuns
- RTX SparkRuns
- DGX SparkRuns
All machines: Mistral Small 4 119B VRAM requirements. Everything that runs here: what can the M5 Ultra 512 GB run?
Other models that run on M5 Ultra 512 GB
Questions
Can Mistral Small 4 119B run on M5 Ultra 512 GB?
Mistral Small 4 119B at FP8 runs on the M5 Ultra 512 GB with 256K of context at about 74 tokens a second.
Report VR-14NWMKA, calculated Nov 22, 2026 from published specs, not benchmarked.