AI News

Unsloth: Qwen4 GGUF will adopt Dynamic 3.1

UnslothUpdated Nov 16 13:53

AI summary

Unsloth stated that the GGUF for Qwen4 will use the new version Unsloth Dynamic 3.1 to achieve the best performance on agent benchmarks such as Terminal Bench and DeepSWE. Previously, Unsloth released the GGUF for Qwen3.8-27B, claiming that the Dynamic V3.1 version leads by an average of 5–10% on the aforementioned benchmarks.

Quoted post

Unsloth AI

@UnslothAI

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://t.co/xIdNwm7CLQ Blog: https://t.co/J2PwgMP6GZ https://t.co/kMy80CVixY

View original

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://t.co/xIdNwm7CLQ Blog: https://t.co/J2PwgMP6GZ https://t.co/kMy80CVixY

View original post

Body

Qwen4 GGUFs will use a new version of Unsloth Dynamic 3.1 for the best performance on Terminal Bench, DeepSWE & more agentic benchmarks.

Source

Unsloth