Nemotron 3.5 Super VL
Intelligence benchmarks
Artificial Analysis indexes - compared with the best open and proprietary models
Intelligence
26.5
AA Index
Intelligence Index - Nemotron 3.5 Super VL vs. the field
Best open-weight models (you can run locally) and leading proprietary models for context.
Benchmark data from Artificial Analysis · updated 2026-10-17.
Hosted API cost & speed
What it costs to rent this model instead of running it locally
| Metric | Value |
|---|---|
| Input (per 1M tokens) | $0.23 |
| Output (per 1M tokens) | $0.57 |
| Median speed (hosted API) | 388 tok/s |
Median across hosted providers, measured by Artificial Analysis - updated 2026-10-17. Local llama.cpp speed depends on your hardware — see the hardware pages for estimates.
Standard benchmarks
Performance across standard evaluations
| Benchmark | Score |
|---|---|
| HLE | 30.7 |
| SciCode | 47.8 |
Source: Artificial Analysis component evals - updated 2026-10-17.
Will it run on your hardware?
Pick your GPU memory - see which quantizations fit, and the cheapest card for the rest
Need an exact figure for your context length? Use the VRAM calculator.
Run it locally
Copy-paste - running in under a minute
vllm serve nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4New to this? Start with Ollama · serve to many users with vLLM.
Deep dive
Notes, sources, and the full write-up
Nemotron 3.5 Super VL is a 65.8B-parameter other model from NVIDIA. It scores 26.5 on the Artificial Analysis Intelligence Index. At Q4_K_M it needs roughly 38 GB of VRAM, placing it in the 24–48 GB hardware tier.
Benchmarks
Artificial Analysis Intelligence Index - Nemotron 3.5 Super VL vs. leading closed models:
| Model | Intelligence | Coding | GPQA |
|---|---|---|---|
| Nemotron 3.5 Super VL | 26.5 | - | - |
| Claude Opus 5.5 | 57.6 | - | - |
| Claude Sonnet 5.5 | 56 | - | - |
| Muse Wonder Full | 55.8 | - | - |
| Claude Fable 5.1 | 53.4 | 81.6 | 93.7 |
| GPT-6 Astra | 52.7 | 76.9 | 96.1 |
Source: Artificial Analysis (2026-10-17).
Popularity
Nemotron 3.5 Super VL has 2,676 downloads in the last month on HuggingFace and 120 likes.
Frequently asked
Quick answers to common questions
How much VRAM does Nemotron 3.5 Super VL need?
Nemotron 3.5 Super VL with 65.8B parameters needs approximately 38 GB at Q4_K_M quantization. Use our VRAM calculator for an exact estimate.
Is Nemotron 3.5 Super VL better than other nvidia models?
Nemotron 3.5 Super VL has 65.8B parameters with 8,192 context - a strong choice for general use.
What license is Nemotron 3.5 Super VL under?
Nemotron 3.5 Super VL is released under the other license, making it suitable for most commercial and personal projects.
What hardware runs Nemotron 3.5 Super VL well?
With 65.8B parameters, Nemotron 3.5 Super VL requires adequate VRAM. High-end GPUs like the RTX 4090 (24GB), RTX 5090 (32GB), or Mac Studio with unified memory are good options. Check our hardware directory for specific recommendations.
What is the best quantization for Nemotron 3.5 Super VL?
Q4_K_M is the recommended sweet spot - ~98% of FP16 quality at ~27% of the size. Q5_K_M (~47 GB) is an option if you have spare VRAM. Use our VRAM calculator to compare.
What models compete with Nemotron 3.5 Super VL?
Nemotron 3.5 Super VL competes with other 33B–99B. Browse our model directory for comparisons, benchmarks, and community reviews to find the best fit.
Nearby options
Similar models and compatible hardware by spec