CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.qwen / Qwen3-4B-ONNX
From: onnx-community <huggingface.co/onnx-community>Newsgroups: alt.freeweights.qwenSubject:

Qwen3-4B-ONNX

Date: 2026-11-14Commit: ca652efSigned: 2DC28CC7B26A283B ✓

Text generation model. Onnx weights, 19.7 GB in all. Published by onnx-community under Apache-2.0.

qwen19.7GBQwen3-4B-ONNXonnxpermissive
FactsParamsnot statedSize19.7 GBFormatsonnxTasktext generationLicenseApache-2.0From sourcepermissive
$ fw get onnx-community/Qwen3-4B-ONNX
# manifest sha256 28c2f037eabd… · 19.7 GB · 40 files
$ fw verify ./Qwen3-4B-ONNX onnx-community/Qwen3-4B-ONNX
From sourceHosted (signed)onnx-community/Qwen3-4B-ONNXLast check: 2026-11-14 21:31 UTC
Run at homeGet help

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

Quantized of Qwen3-4B.

Works with

Run5Convert3Evaluate13Scan12Apps58

Runs with

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

Transformers.jsONNX Runtime GenAIUltralyticsgpu-unlockOpenVINO

Convert with

ONNXOptimumOlive
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
19.7 GB
Weights
501 KB (smallest of 5 ONNX variants)
Parameters
not stated
Formats
onnx
Task
text generation
License
Apache-2.0 (permissive)
Files
40, each with a sha256
Publisher
onnx-community
Added
2026-11-14
Section
alt.freeweights.qwen
Lineage

Original release from the publisher.

Base model: Qwen/Qwen3-4B

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
BadgeHostLast checkResult
From sourcehuggingface.co2026-11-14 21:31 UTCpassed

Model card

From the publisher at commit ca652ef. Shown as plain text with links; images open at the publisher.

https://huggingface.co/Qwen/Qwen3-4B with ONNX weights to be compatible with Transformers.js.

Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using 🤗 Optimum and structuring your repo like this one (with ONNX weights located in a subfolder named onnx).

Files

40 files · 19.7 GBWeights 501 KB (smallest of 5 ONNX variants). Sizes and sha256 from the signed manifest.
Show all 40 files with their sha256
FileSizesha256
.gitattributes2.00 KBfcb302e46be6c3d5a95fae198bb78f0db6e178c5351dcfb6d304ec54ac21c694
README.md519 B22e42c1d314131050e6f5faa57766cf40691afedffff867bb77fa13a366c74f4
added_tokens.json707 Bc0284b582e14987fbd3d5a2cb2bd139084371ed9acbae488829a1c900833c680
chat_template.jinja4.17 KBa55ee1b1660128b7098723e0abcd92caa0788061051c62d51cbe87d9cf1974d8
config.json1.78 KB540fd26e4cc5db26ca6dd1419a08c3cdb3c76fcd59c92487b1f030cbf0c1d78f
generation_config.json219 Bc69f68d9df40786be33f133f1acc377b7ed3cb15a3ab0e137b105e10fd2cd2ed
merges.txt1.67 MB8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5
onnx/model_fp16.onnx722 KBd97869b48ece61af1686aa691e15af27d2a7c1837b968bfebc4ad3b92145c888
onnx/model_fp16.onnx_data2.05 GBd170bf1ebf48f952cbf99be474ce021a1b1b7252550ae1dee5ac762bef50de3b
onnx/model_fp16.onnx_data_12.07 GBff8cd00fbfdf8fedf9c917521ace6620ea175999a8439def0b81206432bb1c72
onnx/model_fp16.onnx_data_22.07 GBbd0c045bf9d0bcd6ac064ce51d8e18388558d58dd32e43c47ae89b6746407f61
onnx/model_fp16.onnx_data_31.87 GB43651e915cb27b2676b97d99e86685260d311ef37849cd34615ca558d7d91858
onnx/model_q4f16.onnx59.8 MBd3e946f9e38577411b0251051c91a1f20c3c0c831e1cf76a13c58ce279d950de
onnx/model_q4f16.onnx_data2.10 GB050398248de4fce7b31b2d2caa909596e4c7aa0f35696270df46b8aaf2209fc8
onnx/model_q4f16.onnx_data_1677 MB363ff5e70ebeb5866afea8eb80b7bdfe22d94d735a8c4d2ebf90c75424c2a410
onnxruntime/cpu_and_mobile/cpu-int4-kld-block-128/chat_template.jinja4.17 KBa55ee1b1660128b7098723e0abcd92caa0788061051c62d51cbe87d9cf1974d8
onnxruntime/cpu_and_mobile/cpu-int4-kld-block-128/config.json9.57 KB0bfeedcfa808cb8404e75d32cef3cdb6c566631acdb7c0edbe9e6945763c6989
onnxruntime/cpu_and_mobile/cpu-int4-kld-block-128/genai_config.json1.52 KBdcb9aa8dd93b1acc17a2df193811c200ab540932c20a98ce4d4d23ce88a69b7d
onnxruntime/cpu_and_mobile/cpu-int4-kld-block-128/model.onnx520 KBb4547cf9327bd532cb81703cf013f958117ba5a3e5a81c7c79a33aba534ff337
onnxruntime/cpu_and_mobile/cpu-int4-kld-block-128/model.onnx.data2.89 GBd6003acd70841b99a44ce4c21d13dc42244e3ec3b7c12d70919f9b55440bbc45
onnxruntime/cpu_and_mobile/cpu-int4-kld-block-128/tokenizer.json11.4 MB979d160e081df25a1bf7f4e2e8f4c441b5dfdc9a8e84aec9f32e80445e1b59b8
onnxruntime/cpu_and_mobile/cpu-int4-kld-block-128/tokenizer_config.json663 Bbfd13b57b2e0c2cb582f311c0895f077d16a868c0dc61e4dbbba544a835341d6
onnxruntime/cuda/cuda-int4-kld-block-128/chat_template.jinja4.17 KBa55ee1b1660128b7098723e0abcd92caa0788061051c62d51cbe87d9cf1974d8
onnxruntime/cuda/cuda-int4-kld-block-128/config.json9.57 KB0bfeedcfa808cb8404e75d32cef3cdb6c566631acdb7c0edbe9e6945763c6989
onnxruntime/cuda/cuda-int4-kld-block-128/genai_config.json1.76 KB481b5b09371642a8d2c2a651fa39b7229e6007affaaf12b249c5e2f3ce84eb55
onnxruntime/cuda/cuda-int4-kld-block-128/model.onnx501 KBb074fc8192970b977761284deb5c7d3db3e47ab92bccbbad44c552f9c2370b29
onnxruntime/cuda/cuda-int4-kld-block-128/model.onnx.data2.81 GB35d01a337b4ec19f5a7e363c6260cf6ddd53102e17169f96099bd29d3fbcd24a
onnxruntime/cuda/cuda-int4-kld-block-128/tokenizer.json11.4 MB979d160e081df25a1bf7f4e2e8f4c441b5dfdc9a8e84aec9f32e80445e1b59b8
onnxruntime/cuda/cuda-int4-kld-block-128/tokenizer_config.json663 Bbfd13b57b2e0c2cb582f311c0895f077d16a868c0dc61e4dbbba544a835341d6
onnxruntime/webgpu/webgpu-int4-kld-block-32/chat_template.jinja4.17 KBa55ee1b1660128b7098723e0abcd92caa0788061051c62d51cbe87d9cf1974d8
onnxruntime/webgpu/webgpu-int4-kld-block-32/config.json9.35 KB875d4ceeae11784f5ee27f4977ae999e1c7ed485fdd4d6d3e567bc178923b4c9
onnxruntime/webgpu/webgpu-int4-kld-block-32/genai_config.json1.75 KB8756bac715c6f1493436e77ea744485eb818f221decc4046abbc74e9274ffc22
onnxruntime/webgpu/webgpu-int4-kld-block-32/model.onnx501 KBbcaf3e1fc7ee93a7dc2eb4d973ea2fbdcabe8f3fb00b589b86d07ab46ab7245a
onnxruntime/webgpu/webgpu-int4-kld-block-32/model.onnx.data3.07 GB18bef60545f9e8703ac0471a433d15ff0a527e172d967e6441283ac08520f9ce
onnxruntime/webgpu/webgpu-int4-kld-block-32/tokenizer.json11.4 MB979d160e081df25a1bf7f4e2e8f4c441b5dfdc9a8e84aec9f32e80445e1b59b8
onnxruntime/webgpu/webgpu-int4-kld-block-32/tokenizer_config.json663 Bbfd13b57b2e0c2cb582f311c0895f077d16a868c0dc61e4dbbba544a835341d6
special_tokens_map.json613 B76862e765266b85aa9459767e33cbaf13970f327a0e88d1c65846c2ddd3a1ecd
tokenizer.json9.12 MBe7a95fce95bf5b0946d0ddb3f9d7caa030b7e850bbe92b0edb26bcf563e9f3d5
tokenizer_config.json10.4 KB1143a0f0c4c262adb96129ba7f7c175c5d6393ad8024a10c0e66c30479cf381f
vocab.json2.78 MBca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
ca652ef636 pinned now manifest updated, same commit2026-11-14 21:31 UTC40 files · 19.7 GB
ca652ef6362026-11-14 21:31 UTC40 files · 19.7 GB

Use it

$ fw get onnx-community/Qwen3-4B-ONNX
# manifest sha256 28c2f037eabd… · 19.7 GB · 40 files
$ fw verify ./Qwen3-4B-ONNX onnx-community/Qwen3-4B-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/Qwen3-4B-ONNX.json --dir ./Qwen3-4B-ONNX $ python3 fw.py verify ./Qwen3-4B-ONNX ./onnx-community__Qwen3-4B-ONNX.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download onnx-community/Qwen3-4B-ONNX --revision ca652ef636e8b121ff4a1607c37ab578cb866987 --local-dir ./Qwen3-4B-ONNX
Run at home

License

Name
Apache License 2.0
Id
Apache-2.0
Class
Permissive
Redistribution
yes
Listing
Hosted (signed)
Decided
Inherited from the base model Qwen/Qwen3-4B: the strictest license along the lineage applies. 2026-11-14
Text in
README.md
Text sha256
22e42c1d314131050e6f5faa57766cf40691afedffff867bb77fa13a366c74f4
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: Qwen3-4B-ONNXDate: 2026-11-14Commit: ca652efSigned: 2DC28CC7B26A283B ✓
Upstream
onnx-community/Qwen3-4B-ONNX
Pinned commit
ca652ef636e8b121ff4a1607c37ab578cb866987
Manifest
Qwen3-4B-ONNX.json · .minisig
Manifest sha256
28c2f037eabda200ffed3853bc82d12b7703496c8fff2740b2fe94297fc7097a
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-14 21:31 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/onnx-community/Qwen3-4B-ONNX.json $ curl -O https://freeweights.allternit.com/manifests/onnx-community/Qwen3-4B-ONNX.json.minisig $ minisign -Vm Qwen3-4B-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/Qwen3-4B · 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/Qwen3-4B-ONNX
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. Qwen3-4B-ONNX.json. Provenance. Takedown history: none.
Source
huggingface.co/onnx-community/Qwen3-4B-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