DeepSeek R1 0528 on M5 Ultra 512 GB: VRAM, speed and fit
DeepSeek R1 0528 at 3-bit runs on the M5 Ultra 512 GB with 160K of context at about 30 tokens a second.
Text generation · Chat · Ollama / LM Studio
Runs comfortably · on M5 Ultra 512 GB · 3-bit (Q3_K_M) · Ollama / LM Studio · Chat
- GPU memory
- 451 GB
- of 512 GB
- Context
- 160K
- auto
- Speed
- 30 tok/s
- 21 when full
- First reply
- 7.9 s
- 2K prompt
Where the memory goes
- Model
- 312 GB
- Context
- 10.7 GB
- Overhead
- 733 MB
- OS
- 128 GB
- Free
- 61.0 GB
- Memory
- 451 GB of 512 GB
- Context
- 160K tokens · auto
- Speed
- 30 tok/s · 21 when full
- First reply
- 7.9 s for a 2K prompt
- Running cost
- $5.06/mo at home · $574/mo on a cloud 8× A40
Validation: Not validated
| Check | Target | Result | Status |
|---|---|---|---|
| Fits in GPU memory | 384 GB usable | 323 GB needed | Pass |
| Headroom | 5% free | 61.0 GB free (16%) | Pass |
| Context for chat | 16K or more | 160K | Pass |
| Writing speed | 15 tok/s or more | 30 tok/s | Pass |
| First reply | under 3 s, 2K prompt | 7.9 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 R1 0528
- Parameters
- 685B, 40.1B active
- Precision
- 3-bit (Q3_K_M)
- Context
- 160K, 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
- $574/mo
- 8× A40 at $4.72/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 bartowski/deepseek-ai_DeepSeek-R1-0528-GGUF- vLLM
vllm serve deepseek-ai/DeepSeek-R1-0528- MLX (Mac)
mlx_lm.chat --model mlx-community/DeepSeek-R1-0528-3bit
DeepSeek R1 0528 on similar machines
- M5 Max 128 GBToo big
- M3 Ultra 96 GBToo big
- M3 Ultra 256 GBRuns
- M3 Ultra 512 GBRuns
- Ryzen AI Max+ 395 64 GBToo big
- Ryzen AI Max+ 395 128 GBToo big
- RTX SparkJust misses
- DGX SparkJust misses
All machines: DeepSeek R1 0528 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 DeepSeek R1 0528 run on M5 Ultra 512 GB?
DeepSeek R1 0528 at 3-bit runs on the M5 Ultra 512 GB with 160K of context at about 30 tokens a second.
Report VR-1VP2C0I, calculated Nov 22, 2026 from published specs, not benchmarked.