7 points | by limondas a day ago ago
4 comments
how about opencode's go ( https://opencode.ai/go ) it is very cost effective and the models are surprisingly competent....
Try qwen3-coder or qwen3-coder-next models which fit into your configuration. This is team-of-experts model which may load only actual experts into GPU.
Thanks for your reply. But it's to big for my PC. In PC around 1.5GB models got 20 token/s , which is too low for agentic workflow.
try latest gemma4:12b. It fits into 16Gb with 256K context window
how about opencode's go ( https://opencode.ai/go ) it is very cost effective and the models are surprisingly competent....
Try qwen3-coder or qwen3-coder-next models which fit into your configuration. This is team-of-experts model which may load only actual experts into GPU.
Thanks for your reply. But it's to big for my PC. In PC around 1.5GB models got 20 token/s , which is too low for agentic workflow.
try latest gemma4:12b. It fits into 16Gb with 256K context window