NVIDIA open-sources Nemotron 3.5 Super VL 120B and Bolt edge models for agents
NVIDIA Blog · rss · 2026-10-15
NVIDIA released Nemotron 3.5 Super VL (120B, open), the fastest and most accurate open model for multimodal agentic tasks in its class (5x faster throughput, 1/5 the size of comparable frontier models), plus Bolt 74B-A9B (24GB, native 2-bit quantization for local agent workloads on RTX/DGX Spark) and Bolt E4B (4GB, due Oct 23). Trained on 26T tokens with open weights/datasets/recipes; adopters include Perplexity, Atlassian, CrowdStrike, Salesforce, Scale AI and Ramp. Serving via Dynamo supports up to 8x more users with 85% lower latency.
More from Models
- ChatGPT web can actually listen to audio, but the same model can't via API or Codex — Possible_Statement84 · 2026-10-23
- MiniMax M3.1 Flash free for 3 days on 0G, with 1M context and 512K output — MiniMax_AI · 2026-10-23
- TLA+ expert corrects Grok: TLC only exhausts finite state spaces, not all behaviors — tianyin_xu · 2026-10-23
- Open LLM cost calculator shows Arabic tokenization and 6x price gaps across models — Moham-saed · 2026-10-23
- OpenAI blocks manual reset with 13% usage left: 'no reset needed right now' — AccomplishedSugar490 · 2026-10-23
- Meta's 816B Muse Spark Open scores 39, losing to 180B Qwen3.8-Flash-Next at 40 — BTA_Labs · 2026-10-23