v0.32.9

Updated September 26, 2026 · 2:47 PM · source date August 11, 2026

Summary

v0.32.9 ollama / ollama Public Notifications You must be signed in to change notification settings Fork 18k Star 182k v0.32.9 dhiltgen released this 11 Aug 13:23 · 172 commits to main since this release v0.32.9 1d5febe NVIDIA Nemotron 3.5 Lightning NVIDIA Nemotron 3.5 Lightning is an open 30B mixture-of-experts (MoE) model with 3B active parameters built for that execution layer of always-on agents. It is designed for harnesses like OpenClaw and Hermes Agent – all supported by the NVIDIA NemoClaw open source security and management stack for running always-on AI agents.

Why it matters

This ProductUpdate is relevant to the technology intelligence record because it involves NVIDIA, GitHub, Llama. The source article should remain the factual reference for follow-up coverage.

Key facts

ollama / ollama Public Notifications You must be signed in to change notification settings Fork 18k Star 182k v0.32.9 dhiltgen released this 11 Aug 13:23 · 172 commits to main since this release v0.32.9 1d5febe NVIDIA Nemotron 3.5 Lightning NVIDIA Nemotron 3.5 Lightning is an open 30B mixture-of-experts (MoE) model with 3B active parameters built for that execution layer of always-on agents.
It is designed for harnesses like OpenClaw and Hermes Agent – all supported by the NVIDIA NemoClaw open source security and management stack for running always-on AI agents.
ollama run nemotron-3.5-lightning What's Changed Added the Nemotron 3 architecture Handle boundary condition in Muse Glimmer function calling parser Full Changelog : v0.32.8...v0.32.9 Assets 18 Loading Uh oh!
There was an error while loading.

Entities in this story

Companies

GitHub→ NVIDIA→

AI models

llama→

Technologies

Open Source→ AI Agents→

Related events