Jan-v1-AIO-GGUF contains two powerful language models: Jan-v1-4B and Jan-v1-edge. Jan-v1-4B is based on the Qwen3-4B-thinking architecture, with 4 billion parameters. It has strong intelligent reasoning, problem-solving, and tool-using capabilities and supports web search tasks. Jan-v1-edge is a lightweight intelligent model designed for fast execution on devices and is suitable for resource-constrained environments.

Natural Language ProcessingTransformersEnglish

Jan-v1-4B-4bit is a 4-bit quantized version converted from the Jan-v1-4B model using mlx-lm version 0.26.3. It is optimized for the Apple MLX framework and provides efficient large language model inference capabilities.

Natural Language ProcessingMlxEnglish