NVIDIA set to launch Nemotron 3.5 Super VL: 120B params, 12B active, image and video input
testingcatalog · x · 2026-10-15
A new NVIDIA model is expected next week, possibly at GTC on Wednesday the 21st — likely Nemotron 3.5 Super VL, which briefly appeared in NVIDIA's own docs before pages were pulled.
- 120B total params, 12B active (hybrid Mamba-Transformer MoE)
- Combines a Nemotron-H hybrid language decoder with a RADIO vision encoder, a vision projector, and a separate temporal video embedder; reuses the Nemotron Omni image/video stack without an audio encoder and retains shared Multi-Token Prediction weights
- Supports image and video input, with a text-only variant as well; a partner issue listed the target release date
More from Models
- Step 5 Preview architecture blog details Sparse GQA with block-wise token merging cutting indexer cost 8x — teortaxesTex · 2026-10-15
- Fish Audio Drama 3 lands in vLLM-Omni: 128 concurrent streams on one H200 — vllm_project · 2026-10-15
- Why is GPT-6 Astra ranked so low on LM Arena? Outscored by GPT-5.6 and 6.1 — AreaExact7824 · 2026-10-15
- Stance test heat map shows Sonnet 5.5 resists framing manipulation other models succumb to — teortaxesTex · 2026-10-15
- Argon (Medium) burned 85% of a 5-hour usage limit in just 5 minutes — Avalunne · 2026-10-15
- Score vs cost chart puts Gemini 4 Argon on the Pareto frontier, Kimi K3 far off it — Hesamation · 2026-10-15