Statistically lossless Qwen3.8 27B GGUF quants drop, UD Q8 matches BF16 at 99.5%
udmrzn · x · 2026-10-27
kaitchup released statistically lossless (SLQ) GGUF quantizations of Qwen3.8 27B, claimed to beat last week's GPTQ versions and built from Unsloth's best UD GGUFs. Notably, Unsloth's UD Q8 K XL matches the original BF16 next-token full-vocab distribution at 99.5% — significantly better than the official FP8. Multiple tiers (EAR98/98.5/99) are live on Hugging Face.
More from Infra
- NVIDIA Launches SimReady Central: 3,500+ Free OpenUSD Simulation Assets on Hugging Face — mishig25 · 2026-10-28
- eMudhra CA bust and PHP2Shell show shipping fast isn't operating well — rseroter · 2026-10-28
- Cadence Q3: recurring revenue up 18% as agents pull work through EDA tools — BenBajarin · 2026-10-28
- Cerebras partners with Oracle to bring its fast AI inference to OCI — vitaliychiley · 2026-10-28
- Meta's PrivacyLib runs billions of privacy checks per second across hundreds of systems — Meta_Engineers · 2026-10-28
- Open-source project claims 97% vector DB compression: 60M chunks from 201GB to 6GB — udmrzn · 2026-10-28