DeepSeek V4 Flash on M3 Ultra 256 GB: VRAM, speed and fit
DeepSeek V4 Flash at FP4 + FP8 runs on the M3 Ultra 256 GB with 1M of context at about 24 tokens a second.
Text generation · Chat · Ollama / LM Studio
Runs comfortably · on M3 Ultra 256 GB · FP4 + FP8 · Ollama / LM Studio · Chat
- GPU memory
- 226 GB
- of 256 GB
- Context
- 1M
- auto
- Speed
- 24 tok/s
- 19 when full
- First reply
- 7.7 s
- 2K prompt
Where the memory goes
- Model
- 155 GB
- Context
- 6.1 GB
- Overhead
- 637 MB
- OS
- 64.0 GB
- Free
- 29.9 GB
- Memory
- 226 GB of 256 GB
- Context
- 1M tokens · auto
- Speed
- 24 tok/s · 19 when full
- First reply
- 7.7 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 | 162 GB needed | Pass |
| Headroom | 5% free | 29.9 GB free (16%) | Pass |
| Context for chat | 16K or more | 1M | Pass |
| Writing speed | 15 tok/s or more | 24 tok/s | Pass |
| First reply | under 3 s, 2K prompt | 7.7 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 V4 Flash
- Parameters
- 284B, 13B active
- Precision
- FP4 + FP8
- Context
- 1M, 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-V4-Flash-0731-GGUF- vLLM
vllm serve deepseek-ai/DeepSeek-V4-Flash-0731- MLX (Mac)
mlx_lm.chat --model mlx-community/DeepSeek-V4-Flash-0731-2.4bit-mixed
DeepSeek V4 Flash on similar machines
- Mac mini M4 Pro 64 GBToo big
- M4 Max 128 GBJust misses
- M5 Max 128 GBJust misses
- 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 GBJust misses
All machines: DeepSeek V4 Flash 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 V4 Flash run on M3 Ultra 256 GB?
DeepSeek V4 Flash at FP4 + FP8 runs on the M3 Ultra 256 GB with 1M of context at about 24 tokens a second.
Report VR-00WHW7R, calculated Nov 22, 2026 from published specs, not benchmarked.