Qwen3.8 2.4T A95B on DGX Station GB300: VRAM, speed and fit
Qwen3.8 2.4T A95B at 1.6-bit runs, spilling into system RAM, on the DGX Station GB300 with 256K of context at about 22 tokens a second.
Text generation · Chat · Ollama / LM Studio
Spills to RAM · on DGX Station GB300 · 1.6-bit (IQ1_S) · Ollama / LM Studio · Chat
255 GB, slower
- GPU memory
- 239 GB
- of 252 GB
- Context
- 256K
- auto
- Speed
- 22 tok/s
- Fast
- First reply
- 4.5 s
- 2K prompt
Where the memory goes
- Model
- 470 GB
- Context
- 23.5 GB
- Overhead
- 1.2 GB
- OS
- 0.0 GB
- Free
- 0.0 GB
- In RAM
- 255 GB
- Memory
- 239 GB of 252 GB · 255 GB in system RAM
- Context
- 256K tokens · auto
- Speed
- 22 tok/s · fast
- First reply
- 4.5 s for a 2K prompt
- Running cost
- $23/mo at home · $1,162/mo on a cloud 4× MI300X
Validation: Validated with conditions
| Check | Target | Result | Status |
|---|---|---|---|
| Fits in GPU memory | 252 GB usable | 495 GB, 255 GB in RAM | Check |
| Headroom | 5% free | GPU full, rest in RAM | Check |
| Context for chat | 16K or more | 256K | Pass |
| Writing speed | 15 tok/s or more | 22 tok/s | Pass |
| First reply | under 3 s, 2K prompt | 4.5 s | Check |
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
- Qwen3.8 2.4T A95B
- Parameters
- 2.4T, 95B active
- Precision
- 1.6-bit (IQ1_S)
- Context
- 256K, 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
- 4× H200 NVL: Runs it with 256K context
- 8× RTX PRO 6000 Blackwell: Runs it with 256K context
Running cost
- At home
- $23/mo
- 1040 W at the wall
- Renting instead
- $1,162/mo
- 4× MI300X at $9.56/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/Qwen3.8-2.4T-A95B-GGUF- vLLM
vllm serve Qwen/Qwen3.8-2.4T-A95B- Model card
- huggingface.co/Qwen/Qwen3.8-2.4T-A95B
Qwen3.8 2.4T A95B on similar machines
- Ryzen AI Max+ 395 128 GBToo big
- RTX SparkToo big
- DGX SparkToo big
- Dual DGX SparkToo big
- 2× RTX PRO 6000 BlackwellToo big
- 4× RTX PRO 6000 BlackwellJust misses
- 8× RTX PRO 6000 BlackwellRuns
- A100 80 GB SXMToo big
All machines: Qwen3.8 2.4T A95B VRAM requirements. Everything that runs here: what can the DGX Station GB300 run?
Other models that run on DGX Station GB300
Questions
Can Qwen3.8 2.4T A95B run on DGX Station GB300?
Qwen3.8 2.4T A95B at 1.6-bit runs, spilling into system RAM, on the DGX Station GB300 with 256K of context at about 22 tokens a second.
Report VR-19GK1FR, calculated Nov 22, 2026 from published specs, not benchmarked.