FastVLM: Efficient Vision Encoding for Vision Language Models
Paper
•
2412.13303
•
Published
•
48
FastVLM
Efficient Vision Encoding for Vision Language Models
-
-
302
FastVLM WebGPU
🍎Real-time video captioning powered by FastVLM
-
apple/FastVLM-0.5B
Text Generation • 0.8B • Updated • 6.65k • 189 -
apple/FastVLM-1.5B
Text Generation • 2B • Updated • 2.04k • 33 -
apple/FastVLM-7B
Text Generation • 8B • Updated • 5.25k • 152
apple/FastVLM-0.5B-fp16
0.6B • Updated • 73 • 6Note MLX checkpoint
apple/FastVLM-1.5B-int8
0.5B • Updated • 61 • 6Note MLX checkpoint
apple/FastVLM-7B-int4
1B • Updated • 73 • 11Note MLX checkpoint