FastVLM: Efficient Vision Encoding for Vision Language Models
Paper
• 2412.13303 • Published
• 75
FastVLM
Efficient Vision Encoding for Vision Language Models
-
-
FastVLM WebGPU
🍎436Real-time video captioning powered by FastVLM
-
apple/FastVLM-0.5B
Text Generation • 0.8B • Updated • 14.4k • 382 -
apple/FastVLM-1.5B
Text Generation • 2B • Updated • 2.24k • 76 -
apple/FastVLM-7B
Text Generation • 8B • Updated • 1.45k • 266
apple/FastVLM-0.5B-fp16
0.6B • Updated • 224 • 23Note MLX checkpoint
apple/FastVLM-1.5B-int8
0.5B • Updated • 232 • 17Note MLX checkpoint
apple/FastVLM-7B-int4
1B • Updated • 73 • 27Note MLX checkpoint