NVIDIA releases Nemotron 3.5 Super VL, an open 120B vision-language model on Kilo
anacondainc · x · 2026-10-17
NVIDIA Nemotron 3.5 Super VL is now available in Kilo by Anaconda. The open vision-language model keeps the 120B-total/12B-active MoE profile (Mamba layers for memory efficiency, transformer layers for reasoning) and adds vision: a RADIO vision encoder, projector, and temporal embedder for video, while retaining Multi-Token Prediction. It offers a 1M-token context (up to 131,072 output tokens), image and video input (screenshots, mockups, charts, MP4), and on-demand thinking (reasoningeffort: off/medium/on), targeting hybrid code/data/visual workflows.
More from Models
- Sentience claims per-user models: train, continually update and serve one model per person — soleio · 2026-10-17
- Four Gemini 4 Argon agents beat Minecraft in 27 hours, writing 2,783 programs — GoogleDeepMind · 2026-10-17
- Meta open-sources Muse Spark Open to mixed reception: 'trash' license, nerfed benchmark scores — gabriberton · 2026-10-17
- If new diffusion models are open-weight only, what's left for commercial use? — blackpanda8484 · 2026-10-17
- Reflection Beam OSS architecture: sliding window attention, gated attention, QK Norm — A_K_Nain · 2026-10-17
- LLMs play a 2D platformer as a decision-making benchmark; 7.9B model only one to clear all 14 levels — Felladrin · 2026-10-17