Qwen3.8-27B called strongest small model: fits a 24GB GPU at Q4 quantization
drdanielbender · x · 2026-11-13
In his open-weight model roundup thread, X user drdanielbender calls Qwen3.8-27B the strongest small model right now: 20 points at just 27B parameters.
- At Q4 quantization it fits on a 24GB GPU like the RTX 3090 or a Mac with 32GB unified memory
- He calls it a genuinely practical local model, and notes AlibabaQwen has teased a Qwen4 open-weight release this month, with Flash-Next already previewing its architecture — a reshuffle is likely
Related event: Four Open-Weight Models Worth Running Locally, from 27B to 2.8T(4 posts)→
More from Models
- HF staffer spotlights basal-2.0-mini, a 1.5B decision-tuned model from Bielik — lhoestq · 2026-11-13
- Observer surprised OpenAI shipped no answer to rival's new model release — jdjohnson · 2026-11-13
- Google's Carbon-Argon-Hydrogen model naming breaks its own size logic — JeremyNguyenPhD · 2026-11-13
- Claude outage: login auth issues hit claude.ai and Claude Code, plus M365 connector errors — op7418 · 2026-11-13
- Microsoft and Claude go down simultaneously, taking apps offline with them — ThePeterMick · 2026-11-13
- Insider teases: Google still has a 'big juicy' model release up its sleeve — iruletheworldmo · 2026-11-13