Qwen3-4B-Instruct

Jane Street's three-player auction game MegaGem was used to train a 4B specialist model, with SFT raising Qwen3-4B-Instruct's benchmark rating from 551 to 1158, ahead of Claude Sonnet 4.6, Claude Opus…

Velora, an open-source macOS dictation tool that runs entirely on-device using Apple Silicon and MLX, has been released under an MIT license. The tool uses Whisper for speech-to-text and a local LLM f…

Researchers propose Tandem Reinforcement Learning (TRL), extending the tandem training paradigm to reinforcement learning with verifiable rewards (RLVR). Training Qwen3-4B-Instruct on competition math…