Alibaba's Qwen line is expanding rapidly, with unannounced model IDs leaking in public repos, official open source confirmation for Qwen 4.0 and 5.0, and a stream of community fine-tunes and dynamic GGUF releases. Qwen is becoming the default backbone for local and self-hosted LLM projects.
NousResearch post-trained Alibaba's Qwen3.8-27B using only supervised fine-tuning, without RL or architectural changes. The resulting model, Arete-27B, cuts propaganda answers from 22% to 0.9% and raises the fact score from 2.32 to 2.98 out of 5, wit...
Unsloth has released new Unsloth Dynamic v3.1 GGUFs for Qwen3.8-Flash-Next, with 10-15% accuracy gains on agentic benchmarks such as DeepSWE and Terminal Bench. It includes a switching process between BF16, Q8_0, Q5_1, and IQ4_NL precisions, with dec...
A pull request in the QwenLM/qwen-code repository shows unannounced model IDs: qwen4-max, qwen4-coder-plus, and qwen4-omni-120b-think, all resolving to a 262,144-token context window. The omni fixture detail confirms the models are not hypothetical, ...
Qwen's head Liu Dayi Heng has denied rumors that future Qwen series would move to API-only releases: Qwen 4.0 and 5.0 will remain open source. With 3 billion downloads, over 460 models, and 300,000 derivatives, the decision strengthens a strategic ec...
