NVIDIA ships open-weight Nemotron 3.5 Bolt 74B-A9B MoE, with mobile-sized E4B on the way
TinfoilTricorn · x · 2026-10-16
NVIDIA AI Dev released two open-weight models: Nemotron 3.5 Bolt 74B-A9B (MoE, 74B total / 9B active) and Nemotron 3.5 Bolt E4B (4GB-class, coming Oct 23, aimed at mobile devices).
- The 74B-A9B is sized like the MoE many have been waiting for, optimized for DGX Spark / GB10 machines with expected day-zero NVFP4 support
- The E4B targets on-device deployment
- The poster notes local-model fans are already running larger Qwen 3.8-flash-next via Strata, so competition exists, but NVIDIA's optimization makes this one worth watching
Related event: NVIDIA Open-Sources Nemotron 3.5 Models, Fitting 120B into 24GB(33 posts)→
More from Infra
- Berkeley scholars: concentrated chip supply chain makes a hardwired frontier AI pause feasible — wfithian · 2026-10-16
- Microsoft trained MAI-Base-2 on 16k GB200 GPUs in just 38 days, with 21% MFU — scaling01 · 2026-10-16
- Robotics data tokenization landscape: Khala maps peaq, THOR, BitRobot and Axis — 0xSammy · 2026-10-16
- Signal65 benchmarks: Intel Xeon 6 runs agent workloads 11% faster for less money — ryanshrout · 2026-10-16
- Microsoft's MAI-Base-2: 2.8T-param MoE pretrained on 16k GB200s in just 38 days — scaling01 · 2026-10-16
- Cloudflare and OpenAI pilot: real-time network signals bring unseen pages into ChatGPT search — irvinebroque · 2026-10-16