Ollama v0.40.10 Adds Nemotron 3.5 Bolt E4B

News LLM Inference InfrastructureAI Agent Infrastructure

  • Ollama v0.40.10 adds NVIDIA’s Nemotron 3.5 Bolt E4B for local use through Ollama.
  • Built on Gemma 4, the vision-language model handles image understanding, tool use, and conversation.
  • It supports a 128K-token context and bundles a DFlash draft for speculative decoding.

Our take

For teams already running Ollama, this offers a local vision-language option to evaluate for workflows involving images and tools. The release notes give no latency or memory measurements, so the practical hardware requirements and the effect of DFlash remain unknown.

Sources

  1. ollama v0.40.10 · Ollama Releases

Further reading

  1. unsloth MOSS-Image, Flint & NVIDIA Bolt E4B · Unsloth Releases

The summary and analysis were generated by AI. The original sources are authoritative. AI content policy