CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.qwen / Qwen2.5-0.5B-Instruct-ONNX-MHA
From: onnx-community <huggingface.co/onnx-community>Newsgroups: alt.freeweights.qwenSubject:

Qwen2.5-0.5B-Instruct-ONNX-MHA

Date: 2026-11-15Commit: b1e71b5Signed: 2DC28CC7B26A283B ✓

Text generation model. Onnx weights, 6.51 GB in all. Published by onnx-community under Apache-2.0.

qwen6.51GBQwen2.5-0.5B-Instruct-ONNX-MHAonnxpermissive
FactsParamsnot statedSize6.51 GBFormatsonnxTasktext generationLicenseApache-2.0From sourcepermissive
$ fw get onnx-community/Qwen2.5-0.5B-Instruct-ONNX-MHA
# manifest sha256 36079c324e2c… · 6.51 GB · 18 files
$ fw verify ./Qwen2.5-0.5B-Instruct-ONNX-MHA onnx-community/Qwen2.5-0.5B-Instruct-ONNX-MHA
From sourceHosted (signed)onnx-community/Qwen2.5-0.5B-Instruct-ONNX-MHALast check: 2026-11-15 05:21 UTC
Run at homeGet help

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

Quantized of Qwen2.5-0.5B-Instruct.

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
6.51 GB
Weights
478 MB (smallest of 8 ONNX variants)
Parameters
not stated
Formats
onnx
Task
text generation
License
Apache-2.0 (permissive)
Files
18, each with a sha256
Publisher
onnx-community
Added
2026-11-15
Section
alt.freeweights.qwen
Lineage

Original release from the publisher.

Base model: Qwen/Qwen2.5-0.5B-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
BadgeHostLast checkResult
From sourcehuggingface.co2026-11-15 05:21 UTCpassed

Model card

From the publisher at commit b1e71b5. Shown as plain text with links; images open at the publisher.

https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct 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

18 files · 6.51 GBWeights 478 MB (smallest of 8 ONNX variants). Sizes and sha256 from the signed manifest.
Hide all 18 files with their sha256
FileSizesha256
.gitattributes1.52 KB11ad7efa24975ee4b0c3c3a38ed18737f0658a5f75a0a96787b576a78a023361
README.md545 Be3c765a817fbecdb2206c2ee18b596c87ff4a48eb60c483550c20ceebfe30751
added_tokens.json605 B58b54bbe36fc752f79a24a271ef66a0a0830054b4dfad94bde757d851968060b
config.json845 B00ed3a4bbcd88ab3a9209ed9f38651e67a3f152421aa1ad33f3216719b72d76c
generation_config.json242 B269039d899c6f3b5e020bf93b35709bf85a1ebd35b7c9817fadfc2ac662b892b
merges.txt1.67 MB8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5
onnx/model.onnx1.98 GBeafa3ff78c945e1da0c75b646600049eca59107e3e9fc2b4d970c7d8bb1f1c20
onnx/model_bnb4.onnx755 MB547207e263ac1c4b81bdc5b28837261e9b1b7e8cf291f1985f6f5d7646a21c1a
onnx/model_fp16.onnx993 MBe4d8b4c593cf9fac804667d34c6972c405b6c83dcca4c7374dd09a4a9a4bcf89
onnx/model_int8.onnx503 MB24d18f7ee4e7bb8e44663f987cfa624413a8bb69b8686e5c52fd8fedbf49e79a
onnx/model_q4.onnx777 MB60e105dee084373137dd810d0d5f47c3a0cfe14c2dd3c25f723fba3169e011f6
onnx/model_q4f16.onnx478 MB2a8e924345337b83796bd98bc130ab0ec0163188d50be55a1bf14b95808c55b8
onnx/model_quantized.onnx503 MBdd7cafab41f5a797c151c559f96ba68dbe7d8d693f944c34149ef32adb652c07
onnx/model_uint8.onnx503 MBdd7cafab41f5a797c151c559f96ba68dbe7d8d693f944c34149ef32adb652c07
special_tokens_map.json613 B76862e765266b85aa9459767e33cbaf13970f327a0e88d1c65846c2ddd3a1ecd
tokenizer.json9.12 MBbb5953180a154511cf4d0fb1fc68a3433f1458aa6db3851ac2609cf41e7d9b5b
tokenizer_config.json7.85 KB6a14243f0ae04884e597b3f032c05e15de9f417318fdcac24ab4e2680e691430
vocab.json2.78 MBca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
b1e71b59c0 pinned now2026-11-15 05:21 UTC18 files · 6.51 GB

Use it

$ fw get onnx-community/Qwen2.5-0.5B-Instruct-ONNX-MHA
# manifest sha256 36079c324e2c… · 6.51 GB · 18 files
$ fw verify ./Qwen2.5-0.5B-Instruct-ONNX-MHA onnx-community/Qwen2.5-0.5B-Instruct-ONNX-MHA
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/onnx-community/Qwen2.5-0.5B-Instruct-ONNX-MHA.json --dir ./Qwen2.5-0.5B-Instruct-ONNX-MHA $ python3 fw.py verify ./Qwen2.5-0.5B-Instruct-ONNX-MHA ./onnx-community__Qwen2.5-0.5B-Instruct-ONNX-MHA.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download onnx-community/Qwen2.5-0.5B-Instruct-ONNX-MHA --revision b1e71b59c0c33ee49eb562303578961795624293 --local-dir ./Qwen2.5-0.5B-Instruct-ONNX-MHA
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/Qwen2.5-0.5B-Instruct: the strictest license along the lineage applies. 2026-11-15
Text in
README.md
Text sha256
e3c765a817fbecdb2206c2ee18b596c87ff4a48eb60c483550c20ceebfe30751
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: Qwen2.5-0.5B-Instruct-ONNX-MHADate: 2026-11-15Commit: b1e71b5Signed: 2DC28CC7B26A283B ✓
Upstream
onnx-community/Qwen2.5-0.5B-Instruct-ONNX-MHA
Pinned commit
b1e71b59c0c33ee49eb562303578961795624293
Manifest
Qwen2.5-0.5B-Instruct-ONNX-MHA.json · .minisig
Manifest sha256
36079c324e2cd7fdeb627dee3335974375c78d78c343e6c7cd10426416adae8b
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 05:21 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/onnx-community/Qwen2.5-0.5B-Instruct-ONNX-MHA.json $ curl -O https://freeweights.allternit.com/manifests/onnx-community/Qwen2.5-0.5B-Instruct-ONNX-MHA.json.minisig $ minisign -Vm Qwen2.5-0.5B-Instruct-ONNX-MHA.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/Qwen2.5-0.5B-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/Qwen2.5-0.5B-Instruct-ONNX-MHA
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. Qwen2.5-0.5B-Instruct-ONNX-MHA.json. Provenance. Takedown history: none.
Source
huggingface.co/onnx-community/Qwen2.5-0.5B-Instruct-ONNX-MHA

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