Can the DGX Spark (GB10) run Qwen3.5 9B?
Yes. Qwen3.5 9B fits the DGX Spark (GB10)'s 128 GB at Q4_K_M (about 7.8 GB needed), running at an estimated 26 tok/s. There's room for up to FP16 if you want higher quality.
Every quantization
Qwen3.5 9B (9.7B) on 128 GB
| Quant | Weights | Needs | Fit | Est. speed |
|---|---|---|---|---|
| Q4_K_M | 6 GB | 7.8 GB | Fits easily | ~26 tok/s |
| Q5_K_M | 7 GB | 8.8 GB | Fits easily | ~22 tok/s |
| Q8_0 | 10 GB | 11.8 GB | Fits easily | ~16 tok/s |
| FP16 | 19 GB | 20.8 GB | Fits easily | ~8.3 tok/s |
Estimates. Needs = weights + 1.8 GB for KV cache and runtime at modest context. Speed is single-stream decode scaled from the DGX Spark (GB10)'s 273.2 GB/s bandwidth (Estimated from memory bandwidth (llama.cpp decode)). Long contexts need more memory and run slower.
Run it
Copy, paste, go
llama-server -hf unsloth/Qwen3.5-9B-GGUF -ngl 99Ollama pulls a Q4 build by default. Pick a larger quant only if the table above says it fits. Full Qwen3.5 9B details →
Compare
Same model, other hardware - and other models on this card
Qwen3.5 9B on other hardware
- RTX 5090~171 tok/s
- RTX 5090 D~171 tok/s
- RTX 6000D~150 tok/s
- RTX 4090~104 tok/s
- Radeon RX 7900 XTX~92 tok/s
- RTX 5080~92 tok/s
- RTX 3090~91 tok/s
- RTX 3080 Ti~87 tok/s
Also runs on the DGX Spark (GB10)
- gpt-oss-120b~35 tok/s
- Qwen2.5 72B~3.9 tok/s
- Llama 3.3 70B~3.9 tok/s
- Qwen3.6 35B A3B~60 tok/s
- Qwen3.5 35B A3B~60 tok/s
- dolphin-2.9.1-yi-1.5-34b~7.8 tok/s
- Gemma 4 31B~8.3 tok/s
- Qwen3 32B~8.3 tok/s
Frequently asked
Quick answers
Can the NVIDIA DGX Spark (GB10) run Qwen3.5 9B?
Yes. Qwen3.5 9B fits the DGX Spark (GB10)'s 128 GB at Q4_K_M (about 7.8 GB needed), running at an estimated 26 tok/s. There's room for up to FP16 if you want higher quality.
How much VRAM does Qwen3.5 9B need?
About 6 GB of weights at Q4_K_M, 10 GB at Q8_0 and 19 GB at FP16. Add roughly 1.8 GB for the KV cache and runtime at modest context lengths.
How fast is Qwen3.5 9B on the DGX Spark (GB10)?
Roughly 26 tokens per second at Q4_K_M (single user, llama.cpp-style decode). This is an estimate from the DGX Spark (GB10)'s 273.2 GB/s memory bandwidth.