Uncensored LFM3-1.7B GGUF quants drop refusal rate from 61.7% to 0%
alexcovo_eth · x · 2026-10-28
Atomic Chat released 'uncensored' dynamic GGUF quants of Liquid AI's LFM3-1.7B (1.1GB and 1.6GB), claiming refusals dropped from 61.7% to 0% with no accuracy loss. The quants are downloadable on Hugging Face for local use — another community abliteration case study on small on-device models.
More from Models
- Kimi K3.1 scores 38% on RareBench, matching GPT-6 Astra at a quarter of the cost — danielmckinn0n · 2026-10-28
- GPT-6 Astra hits SOTA on ARC-AGI-3, inventing its own programming language — typewriters · 2026-10-28
- Abliterated LLMs surge as open-source community strips refusal mechanisms — mishig25 · 2026-10-28
- User Burns Through Four Claude Max x20 Plans, Calls for a $500/Month Tier — andrey_kurenkov · 2026-10-28
- Claude autonomously finds zero-click Linux kernel RCE and dozens of working exploits — burny_tech · 2026-10-28
- Bindu Reddy: Argon Is Bad for Coding Due to Poor Steerability and Hallucinations — bindureddy · 2026-10-28