Gemma on ExitCode0https://exitcode0.net/tags/gemma/Recent content in Gemma on ExitCode0ExitCode0https://exitcode0.net/images/exitcode0-card.jpghttps://exitcode0.net/images/exitcode0-card.jpgHugo -- 0.154.5en-gbTue, 03 Nov 2026 08:30:02 +0000Home Assistant Conversation Agent with a Local Ollama Model: Which Model Workshttps://exitcode0.net/posts/home-assistant-ollama-conversation-agent-local-llm/Tue, 03 Nov 2026 08:30:00 +0000https://exitcode0.net/posts/home-assistant-ollama-conversation-agent-local-llm/Point Home Assistant's Assist at a local Ollama model. I tested gemma4 and qwen3.5 on an RTX 3060 with 18 commands each. One passed all 18, one passed 6.