Nemotron 3.5 Bolt E4B

Headlines · 2

1. Oct 23
   Ollama v0.40.10 Adds NVIDIA Nemotron 3.5 Bolt E4B

   Ollama v0.40.10 adds support for NVIDIA’s Nemotron 3.5 Bolt E4B, a smaller vision-language model based on Gemma 4 and available through Ollama. According to the release notes, the model supports local conversations, image understanding, tool use, a 128K-token context window, and DFlash draft-based speculative decoding. The release also updates Gemma renderers and adds MLX support for Gemma 4 targets.

   Ollama Releases · 🔥 0
2. Oct 19
   Nvidia launches Nemotron 3.5 Super VL and Bolt open-weight models for agents

   Nvidia launched a family of open-weight models aimed at always-on enterprise agents and edge computing, led by Nemotron 3.5 Super VL, a 120-billion-parameter model for enterprise agents. Nvidia says it delivers accuracy similar to the larger Nemotron 3 Ultra on instruction-following and tool use, and claims it completes certain agentic tasks faster than Anthropic and OpenAI models after post-training. Two lightweight Bolt models target local agent work on RTX Spark AI PCs and DGX Spark workstations, with Super VL and Bolt 74B-A9B available now and Bolt E4B due later this month.

   TechCrunch AI · 🔥 0

Experience and discussion from the community

Share my Nemotron 3.5 Bolt E4B experienceAsk about Nemotron 3.5 Bolt E4B