NVIDIA's Nemotron-3.5 Bolt 74B-A9B matches Super within 1% with 9B active params
ryanshrout · x · 2026-10-27
NVIDIA released Nemotron-3.5 Bolt 74B-A9B, aimed at efficient enterprise agentic deployment. Per Signal65's PINNACLE Model Score, it lands within 1% of Nemotron-3.5 Super using 9B active parameters vs 12B, completes more multi-step enterprise jobs (52.5% vs 50.7%), retrieves 93.5% of a 128K corpus, makes 46% fewer weighted errors than Lightning, and is the most token-efficient Nemotron-3.5 model tested.
Related event: NVIDIA Unveils Nemotron-3.5 Bolt, Matching Super with 9B Active Params(2 posts)→
More from Infra
- Llama: tiny menu bar app from the llama.cpp team runs open models on Mac — ggerganov · 2026-10-27
- Local AI build dilemma: 2x used RTX 3090 vs RTX 5080 vs Radeon R9700 for image/video gen — shui95827 · 2026-10-27
- The real AI risk to Indian IT: every dollar earned comes with an OpenAI subscription — NirantK · 2026-10-27
- Local voice agent on a 2015 laptop hits 20-30s latency — advice needed — mesolimbic-bliss · 2026-10-27
- United CEO says passengers are switching airlines just for Starlink internet — XFreeze · 2026-10-27
- Naveen Rao: AI's next chapter is inference, a $10T market within a decade — ravikantagrawal · 2026-10-27