alt.freeweights.qwen / Qwen3-VL-4B-Instruct-ONNX

From:

onnx-community <huggingface.co/onnx-community>Newsgroups: alt.freeweights.qwenSubject:

Qwen3-VL-4B-Instruct-ONNX

Date: 2026-11-15Commit: 3b76cbcSigned: 2DC28CC7B26A283B ✓

Model. Onnx weights, 6.65 GB in all. Published by onnx-community under Apache-2.0.

qwen

6.65GBQwen3-VL-4B-Instruct-ONNXonnxpermissive

FactsParamsnot statedSize6.65 GBFormatsonnxTasknot taggedLicenseApache-2.0From sourcepermissive

$ fw get onnx-community/Qwen3-VL-4B-Instruct-ONNX
# manifest sha256 0363096b7b8d… · 6.65 GB · 30 files
$ fw verify ./Qwen3-VL-4B-Instruct-ONNX onnx-community/Qwen3-VL-4B-Instruct-ONNX

From sourceHosted (signed)onnx-community/Qwen3-VL-4B-Instruct-ONNXLast check: 2026-11-15 05:29 UTC

Run at home Get help

Get help: custom fine-tune or private deploy. We review your setup before we quote.

Quantized of Qwen3-VL-4B-Instruct.

Works with

Run2 Convert3 Scan1

Runs with

Ranked by fit to this model (onnx), then by GitHub stars.

Ultralytics OpenVINO

Convert with

ONNX

Optimum

Olive

Scan with

ModelScan

Overview Model card Files Use it License Provenance Model tree

Overview

Size: 6.65 GB
Weights: 2.34 KB (smallest of 6 ONNX variants)
Parameters: not stated
Formats: onnx
Task: not tagged
License: Apache-2.0 (permissive)
Files: 30, each with a sha256
Publisher: onnx-community
Added: 2026-11-15
Section: alt.freeweights.qwen

Lineage

Original release from the publisher.

Base model: Qwen/Qwen3-VL-4B-Instruct

Where these bytes come from

Publisher at the pinned commit→You

Sources are tried in order. A file counts only when its size and sha256 match the manifest. Sources are checked when you ask for them, not on a timer.

Sources

Badge	Host	Last check	Result
From source	huggingface.co	2026-11-15 05:29 UTC	passed

Model card

From the publisher at commit 3b76cbc. Shown as plain text with links; images open at the publisher.

Qwen3-VL-4B-Instruct ONNX models#

Introduction#

This repository hosts the optimized versions of the Qwen3-VL-4B-Instruct models to accelerate inference with ONNX Runtime.

Optimized models are published here in ONNX format to run with ONNX Runtime on CPU and GPU across devices with the precision best suited to each of these targets.

Here are some of the optimized configurations we have added:

ONNX model for int4 CPU: ONNX model for CPU and mobile using int4 quantization via RTN.
ONNX model for int4 CUDA: ONNX model for CUDA using int4 quantization via RTN.

Model Create#

You can see how to create the ONNX models by following the Olive recipes here for your target hardware.

Model Run#

You can see how to run the examples with ORT GenAI here.

For CPU:

# Download the model directly using the Hugging Face CLI
hf download onnx-community/Qwen3-VL-4B-Instruct-ONNX --include onnxruntime/cpu_and_mobile/cpu-int4-rtn-block-32/* --local-dir .

# Install the CPU package of ONNX Runtime GenAI
pip install --pre onnxruntime-genai

# Please adjust the model directory (-m) accordingly
curl https://raw.githubusercontent.com/microsoft/onnxruntime-genai/main/examples/python/common.py -o common.py
curl https://raw.githubusercontent.com/microsoft/onnxruntime-genai/main/examples/python/model-mm.py -o model-mm.py
python model-mm.py -m onnxruntime/cpu_and_mobile/cpu-int4-rtn-block-32/ -e cpu

For CUDA:

# Download the model directly using the Hugging Face CLI
hf download onnx-community/Qwen3-VL-4B-Instruct-ONNX --include onnxruntime/cuda/cuda-int4-rtn-block-32/* --local-dir .

# Install the CUDA package of ONNX Runtime GenAI
pip install --pre onnxruntime-genai-cuda

# Please adjust the model directory (-m) accordingly
curl https://raw.githubusercontent.com/microsoft/onnxruntime-genai/main/examples/python/common.py -o common.py
curl https://raw.githubusercontent.com/microsoft/onnxruntime-genai/main/examples/python/model-mm.py -o model-mm.py
python model-mm.py -m onnxruntime/cuda/cuda-int4-rtn-block-32/ -e cuda

Model Description#

Developed by: Microsoft
Model type: ONNX
License: Apache 2.0
Model Description: This is a conversion of the Qwen3-VL-4B-Instruct models for ONNX Runtime inference.

Disclaimer: Model is only an optimization of the base model. Any risk associated with the model is the responsibility of the user of the model. Please verify and test for your scenarios. There may be a slight difference in output from the base model with the optimizations applied.

Files

30 files · 6.65 GBWeights 2.34 KB (smallest of 6 ONNX variants). Sizes and sha256 from the signed manifest.

Show all 30 files with their sha256

File	Size	sha256
.gitattributes	1.62 KB	6916ac4a9fd92a5964d49b45d4c87999e8dc7287e6a3073ecc6cba692d7a6615
LICENSE	11.3 KB	832dd9e00a68dd83b3c3fb9f5588dad7dcf337a0db50f7d9483f310cd292e92e
README.md	2.85 KB	16a3d148c4cd54cab20410e91fffc30b1d853bc83d237270f330e4b4fe8d1e8c
config.json	1.50 KB	edac7703329133edfc53e46ac0081835144c99d7eebf28b71c732694d435224d
onnxruntime/cpu_and_mobile/cpu-int4-rtn-block-32/chat_template.jinja	5.41 KB	24a1eb036569714fc3efe7908495159c19ac5138f652c9e524475e40ce87d716
onnxruntime/cpu_and_mobile/cpu-int4-rtn-block-32/config.json	1.59 KB	515c5fc204a21eb086e8ad2f60248edfc537a010240d8cb5c6b74d321514350c
onnxruntime/cpu_and_mobile/cpu-int4-rtn-block-32/embedding.onnx	2.34 KB	0e763665d3c872a8f91f9c5e2c084c9f21d580818d986be6a5813bf9ebab62f2
onnxruntime/cpu_and_mobile/cpu-int4-rtn-block-32/embedding.onnx.data	207 MB	66345e6725ffdd5ba51f693b95ac6d28d4a5e2e70203f970000a21588c5a9d9f
onnxruntime/cpu_and_mobile/cpu-int4-rtn-block-32/genai_config.json	2.80 KB	7d88f9fd77b1a5bd2215ddfe9c841e02bbea808ff5315d530ed27cf27729ad3e
onnxruntime/cpu_and_mobile/cpu-int4-rtn-block-32/generation_config.json	255 B	a91ac8552b94a54736d05df0f9c4df38ea12061b830ceba093327a6577d1528d
onnxruntime/cpu_and_mobile/cpu-int4-rtn-block-32/processor_config.json	1.60 KB	bfd0b54627a192f66186cbe537c04f782b55631135d2e527bad489165a9ce3ca
onnxruntime/cpu_and_mobile/cpu-int4-rtn-block-32/text.onnx	1.35 MB	5782c5f514484cf20b92f455f3f36a46d652e062abb1311db355f8a4989c0e36
onnxruntime/cpu_and_mobile/cpu-int4-rtn-block-32/text.onnx.data	2.52 GB	f73addc1a6d9952b39e172abf5f9b3fe68504e870f1561c45445d3f00cb02c9f
onnxruntime/cpu_and_mobile/cpu-int4-rtn-block-32/tokenizer.json	11.4 MB	83be2230e69d031c94eb1d76bbc99fefac97eef09ab156791a65a66f048ecb83
onnxruntime/cpu_and_mobile/cpu-int4-rtn-block-32/tokenizer_config.json	694 B	4fc29f241a5d042a2508e314991113d4b5ad144558fbb631f4a60899ad8ca1d5
onnxruntime/cpu_and_mobile/cpu-int4-rtn-block-32/vision.onnx	2.95 MB	bb8f7631391fadc7e23ce8536433c128d8a2ad208c8e007e8870760400680758
onnxruntime/cpu_and_mobile/cpu-int4-rtn-block-32/vision.onnx.data	184 MB	486403e1e62348cdcbdc18319027be976aa1e1def09595d36c7734a2c6911ea9
onnxruntime/cuda/cuda-int4-rtn-block-32/chat_template.jinja	5.29 KB	3636d0f0bd6bef02654cdffdc447b79cb2cef8ab02cc75267345946291a489e4
onnxruntime/cuda/cuda-int4-rtn-block-32/config.json	1.53 KB	3bf41aea4ace4e20cb28d9f0d557fd2c53517ef6633cc1e57f49b7685859e512
onnxruntime/cuda/cuda-int4-rtn-block-32/embedding.onnx	2.50 KB	1c3bd5d9a265d5102b465015c8d8e6652b2b577b846a9e1dc2ed9bd90c77f199
onnxruntime/cuda/cuda-int4-rtn-block-32/embedding.onnx.data	778 MB	894430cf9d1953269a321711869f694f40e57bf08ed8d3feb3a0c189e202334a
onnxruntime/cuda/cuda-int4-rtn-block-32/genai_config.json	3.42 KB	e7c4554c261442164c9335ac41e977d632b1cfc0d895909621137f4e60613883
onnxruntime/cuda/cuda-int4-rtn-block-32/generation_config.json	241 B	6dc1a77ae6a62183c362e9cca4712de11a5278ef730f2be47da55662732a67ce
onnxruntime/cuda/cuda-int4-rtn-block-32/processor_config.json	1.53 KB	8d6352783ece74a807d3b3ba4f11f97874d6e0c098be8383b322c2c8d7fb93c3
onnxruntime/cuda/cuda-int4-rtn-block-32/text.onnx	1.55 MB	c236377764cfa01761ebf6de2a4f934059b2d5aebd98d659975434a4198208c0
onnxruntime/cuda/cuda-int4-rtn-block-32/text.onnx.data	2.27 GB	33ab8fdf1eb997ccc86bbaa7cb3a55dc5a6961a09c4fe3dec34fdc880f59da13
onnxruntime/cuda/cuda-int4-rtn-block-32/tokenizer.json	12.2 MB	50d6fedc69f49013248f12956b572a7eea1dc248e22e02994a6d18345d1a9466
onnxruntime/cuda/cuda-int4-rtn-block-32/tokenizer_config.json	665 B	a514bad7480779b076e74e991bbeaee8dc57f3ba813750129ceb6230a88e50c4
onnxruntime/cuda/cuda-int4-rtn-block-32/vision.onnx	254 KB	7a9fcbbca106ad9e6f9e41ac3e31a6c673b799a4192dd68a7868c5bbdd76d1e5
onnxruntime/cuda/cuda-int4-rtn-block-32/vision.onnx.data	667 MB	7d06ee779de1bb4974d3dc97728577a834a3d78237f477d17aab676528c56a44

VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.

Upstream commit	Date	Contents
3b76cbc8c5 pinned now	2026-11-15 05:29 UTC	30 files · 6.65 GB

Use it

$ fw get onnx-community/Qwen3-VL-4B-Instruct-ONNX
# manifest sha256 0363096b7b8d… · 6.65 GB · 30 files
$ fw verify ./Qwen3-VL-4B-Instruct-ONNX onnx-community/Qwen3-VL-4B-Instruct-ONNX

fw.pyChecks the signature and every sha256, tries each source in order, resumes.

$ python3 fw.py get https://freeweights.allternit.com/manifests/onnx-community/Qwen3-VL-4B-Instruct-ONNX.json --dir ./Qwen3-VL-4B-Instruct-ONNX
$ python3 fw.py verify ./Qwen3-VL-4B-Instruct-ONNX ./onnx-community__Qwen3-VL-4B-Instruct-ONNX.json

hfThe Hugging Face CLI with one setting. Same repo id.

$ HF_ENDPOINT=https://freeweights.allternit.com hf download onnx-community/Qwen3-VL-4B-Instruct-ONNX --revision 3b76cbc8c52439369979d4495ce803abf9d3681a --local-dir ./Qwen3-VL-4B-Instruct-ONNX

Run at home

License

Name: Apache License 2.0
Id: Apache-2.0
Class: Permissive
Redistribution: yes
Listing: Hosted (signed)
Decided: License as declared by the publisher. No person read it. 2026-11-15
Text in: LICENSE
Text sha256: 832dd9e00a68dd83b3c3fb9f5588dad7dcf337a0db50f7d9483f310cd292e92e
Terms gate: No extra terms beyond the license.

Read the license text

Licenses are checked against the license table. A custom license passes only after a person reads it.

Provenance

From:

onnx-community <huggingface.co/onnx-community>Newsgroups: alt.freeweights.qwenSubject: Qwen3-VL-4B-Instruct-ONNXDate: 2026-11-15Commit: 3b76cbcSigned: 2DC28CC7B26A283B ✓

Upstream: onnx-community/Qwen3-VL-4B-Instruct-ONNX
Pinned commit: 3b76cbc8c52439369979d4495ce803abf9d3681a
Manifest: Qwen3-VL-4B-Instruct-ONNX.json · .minisig
Manifest sha256: 0363096b7b8d10f21eb825477950d6d73f3469ead8c8e160a3f0cff80df5daa9
Signature: minisign, Ed25519, key 2DC28CC7B26A283B
Created: 2026-11-15 05:29 UTC
Generator: freeweights-manifest/0.1.0
Takedowns: None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/onnx-community/Qwen3-VL-4B-Instruct-ONNX.json
$ curl -O https://freeweights.allternit.com/manifests/onnx-community/Qwen3-VL-4B-Instruct-ONNX.json.minisig
$ minisign -Vm Qwen3-VL-4B-Instruct-ONNX.json -P RWQ7KGqyx4zCLXtUFOqvfv8L3g+8fpKJ1FsuxPyOYMF+4KufbUxKq1Oq
$ shasum -a 256 <file>   # compare with the Files tab

A manifest whose signature fails must be rejected. A file whose size or sha256 does not match must be discarded. Verify a download

Model tree

Parent

Qwen/Qwen3-VL-4B-Instruct · this model is a quantization of it

No model in the catalog names this one as its parent.

Get it

Download

$ HF_ENDPOINT=https://freeweights.allternit.com hf download onnx-community/Qwen3-VL-4B-Instruct-ONNX

Open in Freeweights Studio

Pull, verify and run it in the Allternit app on Desktop, web or phone.

Signed manifest

minisign, key 2DC28CC7B26A283B. Qwen3-VL-4B-Instruct-ONNX.json. Provenance. Takedown history: none.

Source

huggingface.co/onnx-community/Qwen3-VL-4B-Instruct-ONNX

Related models

All of alt.freeweights.qwen →

From:

BAAI <huggingface.co/BAAI>Subject: Aquila-VL-2B-llava-qwen

From: Perciqa <huggingface.co/Perciqa>Subject: Aurora-Code-1

From:

BAAI <huggingface.co/BAAI>Subject: bge-reasoner-embed-qwen3-8b-0923

From: amazon <huggingface.co/amazon>Subject: BMOJOF-primed-HQwen3-8B-Instruct

From: nbeerbower <huggingface.co/nbeerbower>Subject: Bubba-Qwen3.6-27B-LoRA

From: bartowski <huggingface.co/bartowski>Subject: bytkim_Qwen3.8-27B-pi-GGUF