Show HN: Ran Qwen 3.8 27B autonomously(ish) for 3 weeks on single 3090 | Hacker News - But Better

Show HN: Ran Qwen 3.8 27B autonomously(ish) for 3 weeks on single 3090 huggingface.co

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

2 points•iamskeole•10 days ago•0 comments•

#ish #ran #27b #single #autonomously #qwen #weeks #ran qwen

0 comments

No comments yet.

Read the full thread on Hacker News →

Related stories

Unattended 24hr Full-Stack Build: Qwen 3.8 27B on a Single RTX 5090github.com
Hacker News · 2 points · 9 days ago
Bonsai 2 27B: 5.9 GB of weights for a 27B modeltwitter.com
Hacker News · 2 points · 8 days ago
Single-layer, single-head neural transformer written in PDP-11 assembly languagegithub.com
Lobsters · 3 points · 6 months ago
I Ran My Career Like a Production System for 12 Weeks. The Dashboard Was Wrong Before I Was.dev.to
DEV Community · 16 points · 1 day ago
VeriLoop E2 Release: 27B Post-Trained Model and Full GGUF BF16 to IQ1_Mdiscuss.huggingface.co
Hacker News · 1 points · 5 days ago
Bonsai 2 27B: Near-Lossless Compression in a 9x Smaller Footprintprismml.com
Hacker News · 575 points · 13 days ago