DeepSeek V3 on M3 Ultra 256 GB: VRAM, speed and fit
DeepSeek V3 at 1.6-bit runs on the M3 Ultra 256 GB with 160K of context at about 42 tokens a second.
Text generation · Chat · Ollama / LM Studio
Runs comfortably · on M3 Ultra 256 GB · 1.6-bit (IQ1_S) · Ollama / LM Studio · Chat
- GPU memory
- 207 GB
- of 256 GB
- Context
- 160K
- auto
- Speed
- 42 tok/s
- 22 when full
- First reply
- 25 s
- 2K prompt
Where the memory goes
- Model
- 131 GB
- Context
- 10.7 GB
- Overhead
- 733 MB
- OS
- 64.0 GB
- Free
- 49.1 GB
- Memory
- 207 GB of 256 GB
- Context
- 160K tokens · auto
- Speed
- 42 tok/s · 22 when full
- First reply
- 25 s for a 2K prompt
- Running cost
- $3.55/mo at home · $287/mo on a cloud 4× A40
Validation: Not validated
| Check | Target | Result | Status |
|---|---|---|---|
| Fits in GPU memory | 192 GB usable | 143 GB needed | Pass |
| Headroom | 5% free | 49.1 GB free (26%) | Pass |
| Context for chat | 16K or more | 160K | Pass |
| Writing speed | 15 tok/s or more | 42 tok/s | Pass |
| First reply | under 3 s, 2K prompt | 25 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
- DeepSeek V3
- Parameters
- 684B, 40.1B active
- Precision
- 1.6-bit (IQ1_S)
- Context
- 160K, auto
- Chats at once
- 1
- Use
- Chat
- Runs in
- Ollama / LM Studio
- Hardware
- M3 Ultra 256 GB
- GPU can use
- 192 GB of 256 GB
Running cost
- At home
- $3.55/mo
- 162 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/DeepSeek-V3-GGUF- vLLM
vllm serve deepseek-ai/DeepSeek-V3- MLX (Mac)
mlx_lm.chat --model mlx-community/DeepSeek-V3-4bit- Model card
- huggingface.co/deepseek-ai/DeepSeek-V3
DeepSeek V3 on similar machines
- Mac mini M4 Pro 64 GBToo big
- M4 Max 128 GBToo big
- M5 Max 128 GBToo big
- M3 Ultra 96 GBToo big
- M3 Ultra 512 GBRuns
- M5 Ultra 512 GBRuns
- Ryzen AI Max+ 395 64 GBToo big
- Ryzen AI Max+ 395 128 GBToo big
All machines: DeepSeek V3 VRAM requirements. Everything that runs here: what can the M3 Ultra 256 GB run?
Other models that run on M3 Ultra 256 GB
Questions
Can DeepSeek V3 run on M3 Ultra 256 GB?
DeepSeek V3 at 1.6-bit runs on the M3 Ultra 256 GB with 160K of context at about 42 tokens a second.
Report VR-0LW3ZL0, calculated Nov 22, 2026 from published specs, not benchmarked.