Qwen

Ollama v0.35.1-rc0 Adds Explicit Model Capability Declarations

vLLM consolidates as default LLM serving layer across chips, clouds, and consumer GPUs

Red Hat Details FastMTP Heads to Speed vLLM Speculative Decoding

Alibaba Qwen Open-Sources 4B Driving Model Pairing Scene Understanding with Motion Planning

Alibaba Open-Sources Qwen3.8-27B: Frontier-Class AI on 17GB of RAM