Qwen-MLX InsightKeeper/Qwen2.5-7B-Instruct-1M-4bits-DWQ Text Generation • 1B • Updated Jun 2 • 16 InsightKeeper/Qwen2.5-7B-Instruct-1M-4bits-dynamic-DWQ Text Generation • 1B • Updated Jun 8 • 23
FastVLM-MLX Exported model for inference with mlx-vlm based on FastViTHD work from Apple (https://github.com/apple/ml-fastvlm) InsightKeeper/FastVLM-7B-MLX-8bit Updated May 30 • 10 InsightKeeper/FastVLM-0.5B-MLX-4bit 0.1B • Updated May 30 • 10 InsightKeeper/FastVLM-0.5B-MLX-6bit 0.1B • Updated May 30 • 6 InsightKeeper/FastVLM-0.5B-MLX-8bit 0.2B • Updated May 30 • 19
Qwen-MLX InsightKeeper/Qwen2.5-7B-Instruct-1M-4bits-DWQ Text Generation • 1B • Updated Jun 2 • 16 InsightKeeper/Qwen2.5-7B-Instruct-1M-4bits-dynamic-DWQ Text Generation • 1B • Updated Jun 8 • 23
FastVLM-MLX Exported model for inference with mlx-vlm based on FastViTHD work from Apple (https://github.com/apple/ml-fastvlm) InsightKeeper/FastVLM-7B-MLX-8bit Updated May 30 • 10 InsightKeeper/FastVLM-0.5B-MLX-4bit 0.1B • Updated May 30 • 10 InsightKeeper/FastVLM-0.5B-MLX-6bit 0.1B • Updated May 30 • 6 InsightKeeper/FastVLM-0.5B-MLX-8bit 0.2B • Updated May 30 • 19