cd/entity/stey1r· home› entities› stey1r
grep -l @stey1r /news/*.json | wc -l → 1

stey1r

mentions 1 type Organization feed RSS

// recent coverage 1 mentions

09:00
2026-10-03
aiflash.com
large-language-models

LessThink-Qwen3-4B: the same model, with far less thinking [P]

A developer posting as stey1r released LessThink-Qwen3-4B, a post-trained version of Qwen3-4B that uses 44% fewer tokens on reasoning while retaining the base model's knowledge and answer style, with …

// co-occurs with top 2 entities
LessThink-Qwen3-4B 1 Qwen3-4B 1
// topics top 4 topics
large language models 1 ai research 1 machine learning 1 artificial intelligence 1