Toot

Written by Alexander Hanff on 2024-11-13 at 16:20

Qwen2.5-coder:32b has dropped and it is jaw dropingly good - beats OpenAi's GPT-4o and is on par with Claude 3.5 Sonnet (the highest benchmarked model for coding to date).

I got it to generate an entire blogging platform with MFA, threaded comments, categories, front and backend, mongodb storage and bootstrap/jquery front end - in ~5 minutes on Mac Studio M1 Ultra with 128GB of RAM via Ollama with a context window of 96k... astonishingly good.

[#]ai #selfhosted

=> More informations about this toot | View the thread | More toots from thatprivacyguy@eupolicy.social

Mentions

Tags

=> View ai tag | View selfhosted tag

Proxy Information
Original URL
gemini://mastogem.picasoft.net/toot/113476554751081341
Status Code
Success (20)
Meta
text/gemini
Capsule Response Time
299.809501 milliseconds
Gemini-to-HTML Time
0.4976 milliseconds

This content has been proxied by September (ba2dc).