Avatar
jb55 10mo ago

I'm running this qwen 7b param model for a local coding-ai goose agent, seems to be working ok, at least for boilerplate stuff so far.

https://ollama.com/hhao/qwen2.5-coder-tools

Reply to this note

Please Login to reply.

Discussion

a0
nobody 10mo ago

I really want to learn how to code, but it seems so difficult…

Avatar
a1 10mo ago

Curious how it compares to Claude

Avatar
O Expedicionário 10mo ago

Awesome model. Have tried Mistral-nemo? So fast 12B model, https://ollama.com/library/mistral-nemo

Wonder what you think

Avatar
Freedom Technology 10mo ago

I've been wanting to try this model.

77
772f9545... 10mo ago

Superb.

94
Stvu 8mo ago

Yeah the small models really fail compared to SOTA paid for ones…

Not even the 70b or 32b coding ones are passing the test. Not going to replace windsurf with it just yet… sad