DeepSeek V3.2 on DGX Station GB300: VRAM, speed and fit
DeepSeek V3.2 at 2-bit runs on the DGX Station GB300 with 52K of context at about 155 tokens a second.
Text generation · Chat · Ollama / LM Studio
Runs comfortably · on DGX Station GB300 · 2-bit (Q2_K) · Ollama / LM Studio · Chat
- GPU memory
- 239 GB
- of 252 GB
- Context
- 52K
- auto
- Speed
- 155 tok/s
- Very fast
- First reply
- 0.7 s
- 2K prompt
Where the memory goes
- Model
- 234 GB
- Context
- 3.9 GB
- Overhead
- 937 MB
- OS
- 0.0 GB
- Free
- 12.9 GB
- In RAM
- 0.0 GB
- Memory
- 239 GB of 252 GB
- Context
- 52K tokens · auto
- Speed
- 155 tok/s · very fast
- First reply
- 0.7 s for a 2K prompt
- Running cost
- $23/mo at home · $574/mo on a cloud 8× A40
Validation: Validated
| Check | Target | Result | Status |
|---|---|---|---|
| Fits in GPU memory | 252 GB usable | 239 GB needed | Pass |
| Headroom | 5% free | 12.9 GB free (5%) | Pass |
| Context for chat | 16K or more | 52K | Pass |
| Writing speed | 15 tok/s or more | 155 tok/s | Pass |
| First reply | under 3 s, 2K prompt | 0.7 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
- DeepSeek V3.2
- Parameters
- 671B, 37B active
- Precision
- 2-bit (Q2_K)
- Context
- 52K, auto
- Chats at once
- 1
- Use
- Chat
- Runs in
- Ollama / LM Studio
- Hardware
- DGX Station GB300
- GPU can use
- 252 GB of 252 GB
- Spill space
- 480 GB LPDDR5X on the Grace CPU
Worth trying
- 8-bit cache: Room for 104K context
Running cost
- At home
- $23/mo
- 1040 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 unsloth/DeepSeek-V3.2-GGUF- vLLM
vllm serve deepseek-ai/DeepSeek-V3.2- MLX (Mac)
mlx_lm.chat --model mlx-community/DeepSeek-V3.2-4bit- Model card
- huggingface.co/deepseek-ai/DeepSeek-V3.2
DeepSeek V3.2 on similar machines
- Ryzen AI Max+ 395 128 GBToo big
- RTX SparkJust misses
- DGX SparkJust misses
- Dual DGX SparkRuns
- 2× RTX PRO 6000 BlackwellRuns
- 4× RTX PRO 6000 BlackwellRuns
- 8× RTX PRO 6000 BlackwellRuns
- A100 80 GB SXMToo big
All machines: DeepSeek V3.2 VRAM requirements. Everything that runs here: what can the DGX Station GB300 run?
Other models that run on DGX Station GB300
Questions
Can DeepSeek V3.2 run on DGX Station GB300?
DeepSeek V3.2 at 2-bit runs on the DGX Station GB300 with 52K of context at about 155 tokens a second.
Report VR-09I38WB, calculated Nov 22, 2026 from published specs, not benchmarked.