# Unsloth updates compressed Qwen3.8-27B models, claiming accuracy gains

_Published Saturday, November 14, 2026 at 11:18 AM EST · AI · Latest · Tier 2 — Notable_

![Unsloth updates compressed Qwen3.8-27B models, claiming accuracy gains — Primary](https://unsloth.ai/docs/~gitbook/image?url=https%3A%2F%2F2815821428-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Forganizations%252FHpyELzcNe0topgVLGCZY%252Fsites%252Fsite_mXXTe%252Fsocialpreview%252FOeFDVbzp4cgwaId7PbvL%252Funsloth%2520docs%2520pic.png%3Falt%3Dmedia%26token%3Df34a6bcc-db15-449a-bc2d-e0e8f52fe953&width=1200&height=630&sign=9a9d6aae5e35625d4a32adaf8cf74290&sv=3)

Unsloth released updated compressed versions of Qwen3.8-27B on November 11, saying its Dynamic V3.1 preview algorithm improves average accuracy by 5-10% at comparable file sizes. Its tests include Terminal Bench 2.1 and DeepSWE v1.1 for agent tasks, alongside coding and general benchmarks.

The 27B-parameter model supports vision, reasoning and a 256K context window, and can run locally through llama.cpp and Unsloth Desktop. Unsloth says four-bit versions work with 16-19GB of VRAM. Most versions from two-bit through six-bit were updated; three-bit UD3 versions remain unchanged because the company found their performance comparable to UD3.1.

## Sources

- [unsloth.ai](https://unsloth.ai/docs/models/qwen3.8)

---
Canonical: https://techandbusiness.org/newswire/dCbjM-Pke4peTxFLQT2DJj
Published: 2026-11-14T16:18:32.903Z
Story chronology: 2026-11-11T17:06:33.043Z
Retrieved: 2026-11-15T01:02:09.565Z
Publisher: Tech & Business (techandbusiness.org)