Skip to content
ModelListedExternal
Download

Apple Fastvlm Vision Projector 512

A standalone ONNX vision projector extracted from the FastVLM pipeline. Converts image features into the FastVLM multimodal embedding space and is designed for CPU-based image-to-text and vision+language inference.

Sourcehuggingface.co/musk12/apple-fastvlm-vision-projector-512/tree/83131679f54ec6746619ce389334971018b283bc
KindOtherBase modelapple/FastVLM-0.5BVersionVision projector v1 standaloneCgrade

Model source

Kind
Other
File size
484 MB
Base model
apple/FastVLM-0.5B
Version
vVision projector v1 standalone
Updated
Oct 10, 2026
Source
Hugging Face

Source description

Apple FastVLM Vision Projector (512)

A standalone ONNX vision projector extracted from the FastVLM pipeline. Converts image features into the FastVLM multimodal embedding space and is designed for CPU-based image-to-text and vision+language inference.

Model file

  • vision_projector_v1_standalone.onnx

Usage

Use this model to convert images into embeddings for a compatible FastVLM language backbone.

import onnxruntime as ort

session = ort.InferenceSession("vision_projector_v1_standalone.onnx")
# feed in your preprocessed image tensor and run inference

Base model

Derived from apple/FastVLM-0.5B.

Sources

1 source
Hugging FacePrimaryVersion 83131679f54ec6746619ce389334971018b283bc
huggingface.co/musk12/apple-fastvlm-vision-projector-512/tree/83131679f54ec6746619ce389334971018b283bc

Verified Oct 10

Model artifacts

1 artifact

vision_projector_v1_standalone.onnx

onnx · 484 MB · SHA-256 0af5d1fb8dc1…7faf · Hugging Face

Download file

Source excerpts

2 excerpts
ReadmeAug 1huggingface.co/musk12/apple-fastvlm-vision-projector-512

--- license: mit language: - en pipeline_tag: image-feature-extraction tags: - onnx - vision - image-encoder - multimodal - fastvlm - cpu base_model: - apple/FastVLM-0.5B --- # Apple FastVLM Vision Projector (512) A standalone ONNX vision projector extracted from the FastVLM pipeline. Converts image features into the FastVLM multimodal embedding space and is designed for CPU-based image-to-text and vision+language inference. ## Model file - `vision_projector_v1_standalone.onnx` ## Usage Use this model to convert images into embeddings for a compatible FastVLM language backbone. ```python import onnxruntime as ort session = ort.InferenceSession("vision_projector_v1_standalone.onnx") # feed in your preprocessed image tensor and run inference ``` ## Base model Derived from [apple/FastVLM-0.5B](https://huggingface.co/apple/FastVLM-0.5B).

NoteAug 1huggingface.co/musk12/apple-fastvlm-vision-projector-512

Source context: 0 downloads · 0 likes · Pipeline image-feature-extraction · Repo musk12/apple-fastvlm-vision-projector-512