All news

Matching stories Newest first

1. Oct 20
   Lr/LocalLLaMACommunity

   Tess-4.5-27B, a Qwen finetune, claims 25% fewer tokens at the same score

   Community finetune by migtissera built on Qwen3.8-27B, with GGUF files on Hugging Face. The author reports 25% fewer tokens across 150 BenchLocal scenarios and 43% fewer on data extraction, with the same scores claimed.

   • Lab: Alibaba
   • Model: Tess-4.5-27B
   • Model: Qwen3.8-27B
   • Topic: research
   • Topic: open-weights