NVIDIA's open-weight Nemotron 3.5 Super VL (120B MoE, 12B active) lands on Together AI
togethercompute · x · 2026-10-15
Together AI now hosts NVIDIA Nemotron 3.5 Super VL, an open-weight multimodal model for visual reasoning and always-on agents across documents, screens, and video. Specs: unified text/image/document/video understanding, reasoning and tool use with visual context preserved across steps, 120B hybrid MoE with 12B active params, multi-token prediction for faster generation, NVFP4 KV cache for more concurrent long-context sessions, and open weights for post-training.
More from Multimodal
- fal launches Worlds for real-time creation and interaction with AI-generated worlds — Scobleizer · 2026-10-16
- Gummy worms as a physics test: Gemini 4 Argon vs. Claude Opus 5.5 elasticity sims — DynamicWebPaige · 2026-10-16
- 260M-parameter looped diffusion transformer beats 6x larger baselines with 5x less compute — burkov · 2026-10-16
- Seedance 2.5 demo: stretching one second of an explosion into a 30-second shot — LudovicCreator · 2026-10-16
- Octopus Short Film Made with Grok Imagine, Upscaled via Topaz — creatoroff · 2026-10-16
- Open-sourced 61-second computing history film generated entirely by Muse Spark — sophiamyang · 2026-10-16