TalkGemmaNet
13 [ai] by techfan 1d
What open-source LLM are you running locally in 2026? I switched from Llama 3 to Gemma 4 last week and the quality improvement on reasoning tasks is significant. Curious what others are using.
3 replies
mldev 1d
Gemma 4 E4B is my daily driver. Fits in 3GB with Q4 quantization. The 140+ language support is a game changer for my translation project.
coder42 1d
Still on Qwen 3.5 for coding tasks. Nothing beats it for Python generation in my experience. But Gemma 4 is better for general reasoning.
anon 17h
Hi
0/300