Can the RTX 6000D run Nemotron 3.5 Super VL?
Yes. Nemotron 3.5 Super VL fits the RTX 6000D's 84 GB at Q4_K_M (about 39.8 GB needed), running at an estimated 24 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 84 GB
| Quant | Weights | Needs | Fit | Est. speed |
|---|---|---|---|---|
| Q4_K_M | 38 GB | 39.8 GB | Fits easily | ~24 tok/s |
| Q5_K_M | 47 GB | 48.8 GB | Fits easily | ~19 tok/s |
| Q8_0 | 70 GB | 71.8 GB | Tight | ~13 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 RTX 6000D's 1570 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
- MacBook Pro 16" M4 Max~8.2 tok/s
- DGX Spark (GB10)~4.1 tok/s
- RTX Spark N1X (128 GB)~4.1 tok/s
Also runs on the RTX 6000D
- Llama 3.3 70B~23 tok/s
- Qwen3.6 35B A3B~343 tok/s
- Laguna-XS-2.1~47 tok/s
- Gemma 4 31B~47 tok/s
- Qwen3 32B~47 tok/s
- Qwen3-Coder-30B-A3B-Instruct~339 tok/s
- Qwen3-30B-A3B-Instruct-2507~339 tok/s
- Qwen3.6 27B~56 tok/s
Frequently asked
Quick answers
Can the RTX 6000D run Nemotron 3.5 Super VL?
Yes. Nemotron 3.5 Super VL fits the RTX 6000D's 84 GB at Q4_K_M (about 39.8 GB needed), running at an estimated 24 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 RTX 6000D?
Roughly 24 tokens per second at Q4_K_M (single user, llama.cpp-style decode). This is an estimate from the RTX 6000D's 1570 GB/s memory bandwidth.