About
This repository provides a model compiled and optimized for Mobilint NPU hardware.
The model is packaged for deployment on Mobilint’s acceleration stack and is intended to be used within that environment.
Qwen3-VL-4B-Instruct
PUBLIC
Mirrored
This repository provides a model compiled and optimized for Mobilint NPU hardware.
Tasks:image-text-to-textLibraries:transformersLicense:apache-2.0
imported
huggingface
transformers
safetensors
mobilint-qwen3_vl
text-generation
mobilint
image-text-to-text
conversational
custom_code
en
base_model:Qwen/Qwen3-VL-4B-Instruct
base_model:quantized:Qwen/Qwen3-VL-4B-Instruct
license:apache-2.0
region:us
14.3Kdownloads0likestransformersLicense:apache-2.0
Model Card
Edit
Inference Providers
This model isn't deployed by any Inference Provider yet. Deploy this model →
Safetensors details
Format
Safetensors
Model size
4B params
Tasks
image-text-to-text
Source
Mirrored from an external registry.
Last synced 7/29/2026
Model tree for mobilint/Qwen3-VL-4B-Instruct
Base model
Qwen/Qwen3-VL-4B-InstructFiles
main
16 files · 5.7 GBHistory
Security scan in progress for 16 files.
main
16 files · 5.7 GB.gitattributes1.5 KB
.gitignore6 B
chat_template.json5.4 KB
config.json2.1 KB
generation_config.json269 B
merges.txt1.6 MB
model.safetensorsLFS1.4 GB
preprocessor_config.json490 B
proxy_qwen3_vl.py667 B
Qwen3-VL-4B-Instruct_text-W8.mxq3.8 GB
Qwen3-VL-4B-Instruct_vision-W8.mxq430 MB
README.md656 B
tokenizer_config.json10.6 KB
tokenizer.json6.7 MB
video_preprocessor_config.json393 B
vocab.json2.6 MB