yasakani-dev/yasakani: Run Qwen3.8-27B locally on Windows with one NVIDIA RTX GPU: chat and an OpenAI-compatible API. On an RTX 5090 the fastest model averaged 2,298 tok/s on our own JSONL edit task (one request at a time, thinking off, v0.1.4).
Related Stories
RegExr: Temporarily Offline
Hacker News
1 hour ago
Synology Security Advisory
Hacker News
1 hour ago
Rebuilding my local voice assistant pipeline
Hacker News
2 hours ago
Should governments slow frontier AI? Jacob Coxon and Robin Hanson debate [video]
Hacker News
4 hours ago
The 98% Slot Machine: How Paid Advertising Became an Extraction Tax
Hacker News
5 hours ago