Skip to content
View original post on X: Unsloth AIOfficial
Published
40/100

Unsloth releases Dynamic V3.1 GGUFs for Qwen3.8-27B

AIUnsloth AI releases Dynamic V3.1 GGUF quantizations of Qwen3.8-27B, which it says lead by 5–10% on average across Terminal Bench, DeepSWE, and other benchmarks. The company says the models run on 12GB RAM and is working on a better version for Qwen4.
Unsloth AIVerified on XOfficial
@UnslothAI
View on X

Today, we're releasing the highest accuracy Qwen3.8-27B GGUFs.

Our new Dynamic V3.1 GGUFs lead by 5–10% on average across Terminal Bench, DeepSWE & more. We’re working on even better version for Qwen4

Run on 12GB RAM.

GGUF: https://huggingface.co/unsloth/Qwen3.8-27B-GGUF
Blog: https://unsloth.ai/docs/models/qwen3.8

Source details

Unsloth AI · x.comPublished · added here

Original title: Today, we're releasing the highest accuracy Qwen3.8-27B GGUFs.

Topics

Open-source ecosystemChina AIProduct updates