Qwen3-8B GGUF
AI-generated summary Qwen's team published official GGUF quantizations of Qwen3-8B ranging from Q4_K_M through Q8_0 for llama.cpp, Ollama, and LM Studio. The release includes thinking and non-thinking modes in one checkpoint and features a 5 GB Q4_K_M build that makes the model runnable on consumer hardware.