Can the DGX Spark (GB10) run Nemotron 3.5 Super VL?
Yes. Nemotron 3.5 Super VL fits the DGX Spark (GB10)'s 128 GB at Q4_K_M (about 39.8 GB needed), running at an estimated 4.1 tok/s. There's room for up to Q8_0 if you want higher quality.
Every quantization
Nemotron 3.5 Super VL (65.8B) on 128 GB
| Quant | Weights | Needs | Fit | Est. speed |
|---|---|---|---|---|
| Q4_K_M | 38 GB | 39.8 GB | Fits easily | ~4.1 tok/s |
| Q5_K_M | 47 GB | 48.8 GB | Fits easily | ~3.3 tok/s |
| Q8_0 | 70 GB | 71.8 GB | Fits easily | ~2.2 tok/s |
| FP16 | 132 GB | 133.8 GB | Too big | - |
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.
Compare
Same model, other hardware - and other models on this card
Nemotron 3.5 Super VL on other hardware
- RTX 6000D~24 tok/s
- MacBook Pro 16" M4 Max~8.2 tok/s
- RTX Spark N1X (128 GB)~4.1 tok/s
Also runs on the DGX Spark (GB10)
- gpt-oss-120b~35 tok/s
- Llama 3.3 70B~3.9 tok/s
- Qwen3.6 35B A3B~60 tok/s
- Laguna-XS-2.1~8.3 tok/s
- Gemma 4 31B~8.3 tok/s
- Qwen3 32B~8.3 tok/s
- Qwen3-Coder-30B-A3B-Instruct~59 tok/s
- Qwen3-30B-A3B-Instruct-2507~59 tok/s
Frequently asked
Quick answers
Can the NVIDIA DGX Spark (GB10) run Nemotron 3.5 Super VL?
Yes. Nemotron 3.5 Super VL fits the DGX Spark (GB10)'s 128 GB at Q4_K_M (about 39.8 GB needed), running at an estimated 4.1 tok/s. There's room for up to Q8_0 if you want higher quality.
How much VRAM does Nemotron 3.5 Super VL need?
About 38 GB of weights at Q4_K_M, 70 GB at Q8_0 and 132 GB at FP16. Add roughly 1.8 GB for the KV cache and runtime at modest context lengths.
How fast is Nemotron 3.5 Super VL on the DGX Spark (GB10)?
Roughly 4.1 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.