Qwen Code
A powerful command-line AI coding agent designed for Qwen3-Coder models.
An open-source command-line coding agent that uses Qwen models to understand codebases, edit files, execute commands, and automate software-development workflows.
Recent stories
Kev 1.0 introduces Kev-27B and updates Kev-9B with a 64k document window and TypeSafe SDK compatibility. The release includes weights, source code, and fine-tuning and deployment skills.
CUA released Cua-S1-4B-0.2, a multimodal decision model trained with supervised learning and task-completion RL in live environments. CUA reports 92.9% on a frozen GUI-360 split and released adapters and training code.
Kev is an Apache-2.0 family of 0.6B, 4B, and 8B decision models compatible with TypeSafe System One APIs. Its author reports that the 8B model reached 79.6% out-of-domain accuracy versus Jev’s 85.7%, while the 4B model runs on a 32 GB Mac.
A developer reports streaming 60% of Qwen3.8-Flash-Next's experts from disk, running the full Q4 model in 37GB of RAM at 40 tokens per second. A separate H100 deployment reports 160 tokens per second with EAGLE-3.
Transluce trained 8B to 1.1T parameter oversight models to inspect other models’ activations. It reports results improve with additional training, though its oracle still has room to improve on a reward-hacking evaluation.
A LocalLLaMA post ran a 122B Qwen model on an older laptop with llama.cpp. The run had very long load and generation times, while another report put Qwen 3.6 35B at 21 tok/s on a Radeon 7600 after ROCm tuning.