πŸ“‹ #Alibaba has shipped Qwen3-8B as ready-to-run GGUF quantizations on Hugging Face: a compact 8.2B-parameter model from ...

πŸ“‹ #Alibaba has shipped Qwen3-8B as ready-to-run GGUF quantizations on Hugging Face: a compact 8.2B-parameter model from the Qwen3 family that brings flagship-level reasoning to laptops and workstations.⚑ One model, two brains: seamless switching between thinking mode (complex logic, math, coding) and non-thinking mode (fast, general dialogue) within a single model. Toggle per turn with /think and /no_think.#AI #Qwen3 #GGUF #LocalLLM πŸ§΅πŸ‘‡

Read Original

Related