CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.phi / Phi-4-mini-instruct-ONNX-GQA
From: onnx-community <huggingface.co/onnx-community>Newsgroups: alt.freeweights.phiSubject:

Phi-4-mini-instruct-ONNX-GQA

Date: 2026-11-15Commit: 9413299Signed: 2DC28CC7B26A283B ✓

Text generation model. Onnx weights, 30.7 GB in all. Published by onnx-community under MIT.

phi30.7GBPhi-4-mini-instruct-ONNX-GQAonnxpermissive
FactsParamsnot statedSize30.7 GBFormatsonnxTasktext generationLicenseMITFrom sourcepermissive
$ fw get onnx-community/Phi-4-mini-instruct-ONNX-GQA
# manifest sha256 f56d5a69b4e8… · 30.7 GB · 21 files
$ fw verify ./Phi-4-mini-instruct-ONNX-GQA onnx-community/Phi-4-mini-instruct-ONNX-GQA
From sourceHosted (signed)onnx-community/Phi-4-mini-instruct-ONNX-GQALast check: 2026-11-15 05:25 UTC
Run at homeGet help

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

Quantized of Phi-4-mini-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
30.7 GB
Weights
1.57 GB (smallest of 4 ONNX variants)
Parameters
not stated
Formats
onnx
Task
text generation
License
MIT (permissive)
Files
21, each with a sha256
Publisher
onnx-community
Added
2026-11-15
Section
alt.freeweights.phi
Lineage

Original release from the publisher.

Base model: microsoft/Phi-4-mini-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 05:25 UTCpassed

Model card

From the publisher at commit 9413299. Shown as plain text with links; images open at the publisher.

https://huggingface.co/microsoft/Phi-4-mini-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

21 files · 30.7 GBWeights 1.57 GB (smallest of 4 ONNX variants). Sizes and sha256 from the signed manifest.
Show all 21 files with their sha256
FileSizesha256
.gitattributes2.00 KBde8802516965901fef65e50aa7ca84ff015c0dffe0edf0a860ac8d3494c364e5
README.md551 Bd246db36adcb16cb00623c91b95f5ad64f8c0f8a5497a1d6b8a115ee12cc407d
added_tokens.json249 Bd4f2aceb0f20b71dd1f4bcc7e052e4412946bf281840b8f83d39f259571af486
config.json2.63 KB76610c90ce2567a1c40e0c2e97a32a28e4282d0d344a5c3b7a0ade15d796189b
generation_config.json174 Bb7cd59256925e9d7fe4355a59e4c5e20365bea272b2deeca998c262f35abd130
merges.txt2.42 MB856ce61180bb689282eed6b3a6838bb1f438399be23aefe9d20eb379791fb4ad
onnx/model.onnx52.1 MB99f68fa98585d95994b63d00f52f6cc4b2d72800a28e5daf3b2e3324d3cfae1a
onnx/model.onnx_data15.3 GB544ee2b3b7235f10bf8ab4cc503361506229da0a89fd5699b548a7211261d123
onnx/model_fp16.onnx225 KB90fe357dac89134b3aa1cbfd83c20864ff7e26f4da7c5774799e9f1ce0174707
onnx/model_fp16.onnx_data7.70 GBd41fc13815d4a0da358e6d1abf8f50c15764255b364a095203bde2c58aa07e0d
onnx/model_q4.onnx284 KB9af1b535d465ea1ddd9a8eb18f8e27a7df6eb45a51bec3dc820f1ff309891dd3
onnx/model_q4.onnx_data2.46 GBe5e003644ccf8a555bc8a47fb5f1db44be661c75495e6113af1e894afe2642c7
onnx/model_q4.onnx_data_11.57 GB45d0f41ebcc6364e7f38736eff36120b784fbf6217f445857cdf81f09009aa9a
onnx/model_q4.onnx_data_2495 MB34fcd7f4b3e9f680b0a412c26fd1d2819318d7285a260067fc4a624c2c217c9d
onnx/model_q4f16.onnx286 KB3ba424ab1c80f466ce3a96d64bcc61d73ae424d36fdb07fae94261f7b4ff1a2a
onnx/model_q4f16.onnx_data1.57 GB75baf1a640e475f18ea4e0699ed2852824237befb802ad92a3e13660841b9566
onnx/model_q4f16.onnx_data_11.50 GB988b60599c0f9674cd44b0379b7306f304862296a123b0a503e75c5db3a5dd39
special_tokens_map.json587 Baff38493227d813e29fcf8406e8e90062f1f031aa47d589325e9c31d89ac7cc3
tokenizer.json15.5 MB382cc235b56c725945e149cc25f191da667c836655efd0857b004320e90e91ea
tokenizer_config.json2.96 KB76c79ba1828e98a574123dd5de047587219ed8c1ab20702d340bc10a7a32b6bd
vocab.json3.91 MB6cb65a857824fa6615bb1782d95d882617a8bbce1da0317118586b36f39e98bd
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
94132999c7 pinned now2026-11-15 05:25 UTC21 files · 30.7 GB

Use it

$ fw get onnx-community/Phi-4-mini-instruct-ONNX-GQA
# manifest sha256 f56d5a69b4e8… · 30.7 GB · 21 files
$ fw verify ./Phi-4-mini-instruct-ONNX-GQA onnx-community/Phi-4-mini-instruct-ONNX-GQA
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/onnx-community/Phi-4-mini-instruct-ONNX-GQA.json --dir ./Phi-4-mini-instruct-ONNX-GQA $ python3 fw.py verify ./Phi-4-mini-instruct-ONNX-GQA ./onnx-community__Phi-4-mini-instruct-ONNX-GQA.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download onnx-community/Phi-4-mini-instruct-ONNX-GQA --revision 94132999c7b4b52c24b8a80ee0dafd850ed101a1 --local-dir ./Phi-4-mini-instruct-ONNX-GQA
Run at home

License

Name
MIT License
Id
MIT
Class
Permissive
Redistribution
yes
Listing
Hosted (signed)
Decided
Inherited from the base model microsoft/Phi-4-mini-instruct: the strictest license along the lineage applies. 2026-11-15
Text in
README.md
Text sha256
d246db36adcb16cb00623c91b95f5ad64f8c0f8a5497a1d6b8a115ee12cc407d
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.phiSubject: Phi-4-mini-instruct-ONNX-GQADate: 2026-11-15Commit: 9413299Signed: 2DC28CC7B26A283B ✓
Upstream
onnx-community/Phi-4-mini-instruct-ONNX-GQA
Pinned commit
94132999c7b4b52c24b8a80ee0dafd850ed101a1
Manifest
Phi-4-mini-instruct-ONNX-GQA.json · .minisig
Manifest sha256
f56d5a69b4e810772f97fae42908d96f8f7a1ad45b64902eb9bee87449c39d9d
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 05:25 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/onnx-community/Phi-4-mini-instruct-ONNX-GQA.json $ curl -O https://freeweights.allternit.com/manifests/onnx-community/Phi-4-mini-instruct-ONNX-GQA.json.minisig $ minisign -Vm Phi-4-mini-instruct-ONNX-GQA.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

microsoft/Phi-4-mini-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/Phi-4-mini-instruct-ONNX-GQA
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. Phi-4-mini-instruct-ONNX-GQA.json. Provenance. Takedown history: none.
Source
huggingface.co/onnx-community/Phi-4-mini-instruct-ONNX-GQA

Related models

All of alt.freeweights.phi →
From: BAAI <huggingface.co/BAAI>Subject: bunny-phi-2-siglip-lora
From: microsoft <huggingface.co/microsoft>Subject: MediPhi
From: microsoft <huggingface.co/microsoft>Subject: MediPhi-Clinical
From: microsoft <huggingface.co/microsoft>Subject: MediPhi-Guidelines
From: microsoft <huggingface.co/microsoft>Subject: MediPhi-Instruct
From: microsoft <huggingface.co/microsoft>Subject: MediPhi-MedCode