L-Forster/open-jet: An offline coding agent for local models. One command sets up the best model your GPU can run, and on 24 GB+ RTX 30/40/50-series cards Qwen3.8-27B runs up to 1.9x faster than llama.cpp.
Related Stories
French lawmakers approved a tax of €0.055 for every gigabyte of internet traffic
Hacker News
1 hour ago
Shiny Object Syndrome
Hacker News
2 hours ago
We Took over ChatGPT Accounts
Hacker News
2 hours ago
Molly(Signal fork) has not been updated since 3 months and is vulnerable
Hacker News
2 hours ago
Serbia just elected the world's brainiest parliament
Hacker News
2 hours ago