We introduce FastViTHD, a novel hybrid vision encoder designed to output fewer tokens and significantly reduce encoding time for high-resolution images.
Our smallest variant outperforms LLaVA-OneVision-0.5B with 85x faster Time-to-First-Token (TTFT) and 3.4x smaller vision encoder.
Our larger variants using Qwen2-7B LLM outperform recent works like Cambrian-1-8B while using a single image encoder with a 7.9x faster TTFT.
Evaluations
Benchmark
FastVLM-0.5B
FastVLM-1.5B
FastVLM-7B
Ai2D
68.0
77.4
83.6
ScienceQA
85.2
94.4
96.7
MMMU
33.9
37.8
45.4
VQAv2
76.3
79.1
80.8
ChartQA
76.0
80.1
85.0
TextVQA
64.5
70.4
74.9
InfoVQA
46.4
59.7
75.8
DocVQA
82.5
88.3
93.2
OCRBench
63.9
70.2
73.1
RealWorldQA
56.1
61.2
67.2
SeedBench-Img
71.0
74.2
75.4
Usage Example
The model has been exported to run with MLX. Follow the instructions in the official repository to use it in an iOS or macOS app.
Citation
If you found this model useful, please cite the following paper:
@InProceedings{fastvlm2025,
author = {Pavan Kumar Anasosalu Vasu, Fartash Faghri, Chun-Liang Li, Cem Koc, Nate True, Albert Antony, Gokul Santhanam, James Gabriel, Peter Grasch, Oncel Tuzel, Hadi Pouransari},
title = {FastVLM: Efficient Vision Encoding for Vision Language Models},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2025},
}
Runs of apple FastVLM-7B-int4 on huggingface.co
112
Total runs
0
24-hour runs
12
3-day runs
24
7-day runs
24
30-day runs
More Information About FastVLM-7B-int4 huggingface.co Model
FastVLM-7B-int4 huggingface.co is an AI model on huggingface.co that provides FastVLM-7B-int4's model effect (), which can be used instantly with this apple FastVLM-7B-int4 model. huggingface.co supports a free trial of the FastVLM-7B-int4 model, and also provides paid use of the FastVLM-7B-int4. Support call FastVLM-7B-int4 model through api, including Node.js, Python, http.
FastVLM-7B-int4 huggingface.co is an online trial and call api platform, which integrates FastVLM-7B-int4's modeling effects, including api services, and provides a free online trial of FastVLM-7B-int4, you can try FastVLM-7B-int4 online for free by clicking the link below.
apple FastVLM-7B-int4 online free url in huggingface.co:
FastVLM-7B-int4 is an open source model from GitHub that offers a free installation service, and any user can find FastVLM-7B-int4 on GitHub to install. At the same time, huggingface.co provides the effect of FastVLM-7B-int4 install, users can directly use FastVLM-7B-int4 installed effect in huggingface.co for debugging and trial. It also supports api for free installation.