Qwen3.5 397B A17B on Dual DGX Spark: VRAM, speed and fit
Qwen3.5 397B A17B at 3-bit runs on the DGX Spark 128 GB with 256K of context at about 21 tokens a second.
Text generation · Chat · Ollama / LM Studio
Runs comfortably · on DGX Spark 128 GB · 3-bit (Q3_K_M) · Ollama / LM Studio · Chat
- GPU memory
- 208 GB
- of 256 GB
- Context
- 256K
- auto
- Speed
- 21 tok/s
- 11 when full
- First reply
- 2.4 s
- 2K prompt
Where the memory goes
- Model
- 184 GB
- Context
- 7.7 GB
- Overhead
- 1.4 GB
- OS
- 15.4 GB
- Free
- 47.9 GB
- Memory
- 208 GB of 256 GB
- Context
- 256K tokens · auto
- Speed
- 21 tok/s · 11 when full
- First reply
- 2.4 s for a 2K prompt
- Running cost
- $3.15/mo at home · $574/mo on a cloud 8× A40
Validation: Validated
| Check | Target | Result | Status |
|---|---|---|---|
| Fits in GPU memory | 241 GB usable | 193 GB needed | Pass |
| Headroom | 5% free | 47.9 GB free (20%) | Pass |
| Context for chat | 16K or more | 256K | Pass |
| Writing speed | 15 tok/s or more | 21 tok/s | Pass |
| First reply | under 3 s, 2K prompt | 2.4 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
- Qwen3.5 397B A17B
- Parameters
- 403B, 17B active
- Precision
- 3-bit (Q3_K_M)
- Context
- 256K, auto
- Chats at once
- 1
- Use
- Chat
- Runs in
- Ollama / LM Studio
- Hardware
- DGX Spark 128 GB
- GPU can use
- 241 GB of 256 GB
Running cost
- At home
- $3.15/mo
- 144 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/Qwen3.5-397B-A17B-GGUF- vLLM
vllm serve Qwen/Qwen3.5-397B-A17B- MLX (Mac)
mlx_lm.chat --model mlx-community/Qwen3.5-397B-A17B-4bit- Model card
- huggingface.co/Qwen/Qwen3.5-397B-A17B
Qwen3.5 397B A17B on similar machines
- Ryzen AI Max+ 395 64 GBToo big
- Ryzen AI Max+ 395 128 GBRuns
- RTX SparkRuns
- DGX SparkRuns
- DGX Station GB300Runs
- 2× RTX PRO 6000 BlackwellRuns
- 4× RTX PRO 6000 BlackwellRuns
- 8× RTX PRO 6000 BlackwellRuns
All machines: Qwen3.5 397B A17B VRAM requirements. Everything that runs here: what can the Dual DGX Spark run?
Other models that run on Dual DGX Spark
Questions
Can Qwen3.5 397B A17B run on Dual DGX Spark?
Qwen3.5 397B A17B at 3-bit runs on the DGX Spark 128 GB with 256K of context at about 21 tokens a second.
Report VR-1US3BP2, calculated Nov 22, 2026 from published specs, not benchmarked.