Model updates

Official news, first rumor reports and substantive progress. Each entry keeps the information published at that time.

• Ollama v0.40.13 brings Liquid AI LFM3 models to Linux and Windows

  Ollama’s v0.40.13 GitHub release says Liquid AI’s LFM3 models, including text-to-speech in lfm3-audio and lfm3-omni, now run on Linux and Windows as well as Apple silicon. Changelog spans v0.40.12…v0.40.13.

  OfficialOfficial updateOct 28Source: ollamaPart of Ollama
• Ollama v0.40.10 adds NVIDIA Nemotron 3.5 Bolt E4B for local vision-language use

  Ollama v0.40.10 ships NVIDIA’s Nemotron 3.5 Bolt E4B, a Gemma 4-based vision-language model for local chat, image understanding, and tool use with a 128K context window and a DFlash draft for speculative decoding (`ollama run nemotron-3.5-bolt:e4b`).

  OfficialOfficial updateOct 23Source: ollamaPart of Ollama
• Ollama v0.40.3-rc0 pauses background model compatibility migrations to cut high-volume overhead

  Ollama’s v0.40.3-rc0 release pauses background model upgrades that were adding overhead on every request in high-volume use such as embeddings (PR #18908), and stops `ollama launch claude` / `ollama launch codex` from showing connector and service-tier warnings.

  OfficialOfficial updateOct 11Source: OllamaPart of Ollama
• Ollama v0.40.2 adds oxi to community integrations and hides duplicate/downgrade guards from model list

  Ollama v0.40.2 updates the README to list oxi among community integrations and hides duplicate and downgrade guards from the model list server-side.

  OfficialOfficial updateOct 9Source: OllamaPart of Ollama

RSS for this view →