FastVLM: Efficient Vision Encoding for Vision Language Models
Paper • 2412.13303 • Published • 76
FastVLM
Efficient Vision Encoding for Vision Language Models
-
-
FastVLM WebGPU
🍎446Real-time video captioning powered by FastVLM
-
apple/FastVLM-0.5B
Text Generation • 0.8B • Updated • 13.8k • 390 -
apple/FastVLM-1.5B
Text Generation • 2B • Updated • 2.97k • 80 -
apple/FastVLM-7B
Text Generation • 8B • Updated • 1.69k • 270
apple/FastVLM-0.5B-fp16
0.6B • Updated • 446 • 27Note MLX checkpoint
apple/FastVLM-1.5B-int8
0.5B • Updated • 211 • 20Note MLX checkpoint
apple/FastVLM-7B-int4
1B • Updated • 67 • 31Note MLX checkpoint