(developers.googleblog.com)

602 points emrah | 1 comments | 20 Apr 25 12:22 UTC | HN request time: 0.211s | source

1. mattfrommars ◴[21 Apr 25 02:15 UTC] No.43747991[source]▶

anyone had success using Gemma 3 QAT models on Ollama with cline? They just don't work as good compared Gemini 2.0 flash provided by API

Gemma 3 QAT Models: Bringing AI to Consumer GPUs