Researchers flag Qwen models as weird, 0.6B post-trained version 'somewhat fried'
lateinteraction · x · 2026-11-04
In a follow-up discussion, researchers confirm that Qwen base models behave oddly — and lateinteraction adds that the instruct/post-trained versions are also very weird, with the 0.6B model being 'somewhat fried.' A first-hand anecdote about Qwen small-model behavior quirks.
Related event: 0.6B post-trained model's poor MATH scores traced to a weight bug(3 posts)→
More from Models
- Open-source TTS: Phonon models under 50M params run on-device with 7ms latency — alex_verem · 2026-11-05
- ElevenLabs sweeps all 5 new Voice Arena TTS leaderboards by 11-26 Elo points — alex_verem · 2026-11-05
- BioSimBench: frontier LLMs ace biology benchmarks but fail at predicting real cell experiments — alex_verem · 2026-11-05
- Kimi K3.1 Pro gains less from test-time compute than Opus 5.0, data shows — teortaxesTex · 2026-11-05
- Grok and Claude Now Refuse to Root Your Own Devices, Citing Brick Risk — doooyle · 2026-11-05
- Nace AI offers 120% cashback to switch teams to Drex Max, claims 11x cost edge over Claude Code — testingcatalog · 2026-11-05