Qwen3 VL 235B A22B Instruct on DGX Station GB300: VRAM, speed and fit
Qwen3 VL 235B A22B Instruct at 8-bit runs on the DGX Station GB300 with 28K of context at about 97 tokens a second.
Text generation · Chat · Ollama / LM Studio
Runs comfortably · on DGX Station GB300 · 8-bit (Q8_0) · Ollama / LM Studio · Chat
- GPU memory
- 239 GB
- of 252 GB
- Context
- 28K
- auto
- Speed
- 97 tok/s
- Very fast
- First reply
- 0.4 s
- 2K prompt
Where the memory goes
- Model
- 233 GB
- Context
- 5.1 GB
- Overhead
- 886 MB
- OS
- 0.0 GB
- Free
- 12.8 GB
- In RAM
- 0.0 GB
- Memory
- 239 GB of 252 GB
- Context
- 28K tokens · auto
- Speed
- 97 tok/s · very fast
- First reply
- 0.4 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 | 12.8 GB free (5%) | Pass |
| Context for chat | 16K or more | 28K | Pass |
| Writing speed | 15 tok/s or more | 97 tok/s | Pass |
| First reply | under 3 s, 2K prompt | 0.4 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
- Qwen3 VL 235B A22B Instruct
- Parameters
- 236B, 22B active
- Precision
- 8-bit (Q8_0)
- Context
- 28K, 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 52K 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/Qwen3-VL-235B-A22B-Instruct-GGUF- vLLM
vllm serve Qwen/Qwen3-VL-235B-A22B-Instruct
Qwen3 VL 235B A22B Instruct on similar machines
- Ryzen AI Max+ 395 128 GBRuns
- RTX SparkRuns
- DGX SparkRuns
- Dual DGX SparkRuns
- 2× RTX PRO 6000 BlackwellRuns
- 4× RTX PRO 6000 BlackwellRuns
- 8× RTX PRO 6000 BlackwellRuns
- A100 80 GB SXMJust misses
All machines: Qwen3 VL 235B A22B Instruct VRAM requirements. Everything that runs here: what can the DGX Station GB300 run?
Other models that run on DGX Station GB300
Questions
Can Qwen3 VL 235B A22B Instruct run on DGX Station GB300?
Qwen3 VL 235B A22B Instruct at 8-bit runs on the DGX Station GB300 with 28K of context at about 97 tokens a second.
Report VR-02VNE7I, calculated Nov 22, 2026 from published specs, not benchmarked.