CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.phi / Phi-3-mini-4k-instruct-onnx-web
From: microsoft <huggingface.co/microsoft>Newsgroups: alt.freeweights.phiSubject:

Phi-3-mini-4k-instruct-onnx-web

Date: 2026-11-15Commit: 80a2792Signed: 2DC28CC7B26A283B ✓

Text generation model. Onnx weights, 5.02 GB in all. Published by microsoft under MIT.

phi5.02GBPhi-3-mini-4k-instruct-onnx-webonnxpermissive
FactsParamsnot statedSize5.02 GBFormatsonnxTasktext generationLicenseMITFrom sourcepermissive
$ fw get microsoft/Phi-3-mini-4k-instruct-onnx-web
# manifest sha256 fd1e1ab7a362… · 5.02 GB · 15 files
$ fw verify ./Phi-3-mini-4k-instruct-onnx-web microsoft/Phi-3-mini-4k-instruct-onnx-web
From sourceHosted (signed)microsoft/Phi-3-mini-4k-instruct-onnx-webLast check: 2026-11-15 03:47 UTC
Run at homeGet help

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

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
5.02 GB
Weights
2.29 GB (smallest of 2 ONNX variants)
Parameters
not stated
Formats
onnx
Task
text generation
License
MIT (permissive)
Files
15, each with a sha256
Publisher
microsoft
Added
2026-11-15
Section
alt.freeweights.phi
Lineage

Original release from the publisher.

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 03:47 UTCpassed

Model card

From the publisher at commit 80a2792. Shown as plain text with links; images open at the publisher.

Phi-3 Mini-4K-Instruct ONNX model for in-browser inference#

Running Phi3-mini-4K entirely in the browser! Check out this demo.

This repository hosts the optimized Web version of ONNX Phi-3-mini-4k-instruct model to accelerate inference in the browser with ONNX Runtime Web.

The Phi-3-Mini-4K-Instruct is a 3.8B parameters, lightweight, state-of-the-art open model trained with the Phi-3 datasets that includes both synthetic data and the filtered publicly available websites data with a focus on high-quality and reasoning dense properties. When assessed against benchmarks testing common sense, language understanding, math, code, long context and logical reasoning, Phi-3 Mini-4K-Instruct showcased a robust and state-of-the-art performance among models with less than 13 billion parameters.

How to run#

ONNX Runtime Web is a JavaScript library to enable web developers to deploy machine learning models directly in web browsers, offering multiple backends leveraging hardware acceleration. WebGPU backend is recommended to run Phi-3-mini efficiently.

Here is an E2E example for running this optimized Phi3-mini-4K for the web, with ONNX Runtime harnessing WebGPU.

Supported devices and browser with WebGPU: Chrome 113+ and Edge 113+ for Mac, Windows, ChromeOS, and Chrome 121+ for Android. Pls visit here for tracking WebGPU support in browsers

Performance Metrics#

Performance vary between GPUs. The more powerful the GPU, the faster the speed. On a NVIDIA GeForce RTX 4090: ~42 tokens/second

Additional Details#

To obtain other optimized Phi3-mini-4k ONNX models for server platforms, Windows, Linux, Mac desktops, and mobile, please visit Phi-3-mini-4k-instruct onnx model. The model differences in the web version compared to other versions:

  1. the model is fp16 with int4 block quantization for weights
  2. the 'logits' output is fp32
  3. the model uses MHA instead of GQA
  4. onnx and external data file need to stay below 2GB to be cacheable in chromium

To optimize a fine-tuned Phi3-mini-4k model to run with ONNX Runtime Web, please follow this Olive example. Olive is an easy-to-use model optimization tool for generating an optimized ONNX model to efficiently run with ONNX Runtime across platforms.

Model Description#

  • Developed by: Microsoft
  • Model type: ONNX
  • Inference Language(s) (NLP): JavaScript
  • License: MIT
  • Model Description: This is the web version of the Phi-3 Mini-4K-Instruct model for ONNX Runtime inference.

Model Card Contact#

guschmue, qining

Files

15 files · 5.02 GBWeights 2.29 GB (smallest of 2 ONNX variants). Sizes and sha256 from the signed manifest.
Hide all 15 files with their sha256
FileSizesha256
.gitattributes1.68 KB2d713ff47a43c82b39cb1803e822679c4285458303435919ab20cc0add4e4e74
LICENSE12.7 KB036571bdc3d7bea4a1f40d48943cda002b42b4ddf3aa7ec93b0759721ac1aed6
README.md3.37 KB7ed5e2a13e48750016eff864815015305c0871c486e68771b2eb40495522c317
added_tokens.json306 Bf8e5a880c6c563a126d9efacb654e105fc4b66f21e5a540f04436e9487a955fb
config.json952 B8fb0de5260c5aa5edd5b128ace631395c3be8cdc632164c943b97117de6e54b5
genai_config.json1.71 KBa311505e830c34c73d8b98bc8313beaf315923d2bf472b1bddba23f523c5d2b6
generation_config.json183 B05b38e12bfeac6482dc04655edd70ee535da4e62ddcbdf075297428a218f9058
onnx/model_q4.onnx1.06 GB16b8e5d28a757c37bbfa7d9420fd094c0c20e3615ca3c203b5b9501015045c8f
onnx/model_q4.onnx_data1.66 GB41d30b87f06b52e6b24c4e2e65a6a14e5c9fb5bc6f495fac17b19c6bc7875ff5
onnx/model_q4f16.onnx838 MBe726f1c300be9714987ebf7cb047afcb002f6ce9a28af1771d05d5d1d4eeaf48
onnx/model_q4f16.onnx_data1.45 GB62eb6a6870961b0039732d574779e44a7de42e26c04ca1433759728d644cc00f
special_tokens_map.json597 B79ebeb996f91ced82d3062d5deb289cf30d04824ff5e853065d616f83356f345
tokenizer.json1.94 MB8e9e94300b0c19471520eca5e6cacc4a522c7da823edac3b2cdd1152b4fb3ae2
tokenizer.model500 KB9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
tokenizer_config.json3.30 KB5e1bcaa42cf573a3ae063f8bb2d54bd5aaf8150155c4670b29aa2caa012ef3b1
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
80a2792f5b pinned now2026-11-15 03:47 UTC15 files · 5.02 GB

Use it

$ fw get microsoft/Phi-3-mini-4k-instruct-onnx-web
# manifest sha256 fd1e1ab7a362… · 5.02 GB · 15 files
$ fw verify ./Phi-3-mini-4k-instruct-onnx-web microsoft/Phi-3-mini-4k-instruct-onnx-web
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/microsoft/Phi-3-mini-4k-instruct-onnx-web.json --dir ./Phi-3-mini-4k-instruct-onnx-web $ python3 fw.py verify ./Phi-3-mini-4k-instruct-onnx-web ./microsoft__Phi-3-mini-4k-instruct-onnx-web.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download microsoft/Phi-3-mini-4k-instruct-onnx-web --revision 80a2792f5bf861528ce9b449b3230f1bd3fdc759 --local-dir ./Phi-3-mini-4k-instruct-onnx-web
Run at home

License

Name
MIT License
Id
MIT
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
036571bdc3d7bea4a1f40d48943cda002b42b4ddf3aa7ec93b0759721ac1aed6
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: microsoft <huggingface.co/microsoft>Newsgroups: alt.freeweights.phiSubject: Phi-3-mini-4k-instruct-onnx-webDate: 2026-11-15Commit: 80a2792Signed: 2DC28CC7B26A283B ✓
Upstream
microsoft/Phi-3-mini-4k-instruct-onnx-web
Pinned commit
80a2792f5bf861528ce9b449b3230f1bd3fdc759
Manifest
Phi-3-mini-4k-instruct-onnx-web.json · .minisig
Manifest sha256
fd1e1ab7a362aeb18fdd3267e1a67d289f5e9d6ce932a51636ebd5a149da840d
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 03:47 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/microsoft/Phi-3-mini-4k-instruct-onnx-web.json $ curl -O https://freeweights.allternit.com/manifests/microsoft/Phi-3-mini-4k-instruct-onnx-web.json.minisig $ minisign -Vm Phi-3-mini-4k-instruct-onnx-web.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

No related models in this catalog.Nothing here lists this model as its parent, and it names no parent.
Get it
Download
$ HF_ENDPOINT=https://freeweights.allternit.com hf download microsoft/Phi-3-mini-4k-instruct-onnx-web
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. Phi-3-mini-4k-instruct-onnx-web.json. Provenance. Takedown history: none.
Source
huggingface.co/microsoft/Phi-3-mini-4k-instruct-onnx-web

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