Nemotron 3.5 Super VL
Oct 2026 License: OpenMDW 1.1
NVIDIA's large hybrid Mamba-Transformer mixture-of-experts model with vision. Strong at reasoning, coding, and documents, with up to 1M context.
Sizes
| Nemotron 3.5 Super VL 120B-A12B Q8_0 requires 192 GB+ memory | 128.5 GB |