CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.phi / Phi-3-vision-128k-instruct-onnx
From: microsoft <huggingface.co/microsoft>Newsgroups: alt.freeweights.phiSubject:

Phi-3-vision-128k-instruct-onnx

Date: 2026-11-15Commit: d8d8eb5Signed: 2DC28CC7B26A283B ✓

Model. Onnx weights, 5.82 GB in all. Published by microsoft under MIT.

phi5.82GBPhi-3-vision-128k-instruct-onnxonnxpermissive
FactsParamsnot statedSize5.82 GBFormatsonnxTasknot taggedLicenseMITFrom sourcepermissive
$ fw get microsoft/Phi-3-vision-128k-instruct-onnx
# manifest sha256 7c08ccc62c6f… · 5.82 GB · 30 files
$ fw verify ./Phi-3-vision-128k-instruct-onnx microsoft/Phi-3-vision-128k-instruct-onnx
From sourceHosted (signed)microsoft/Phi-3-vision-128k-instruct-onnxLast check: 2026-11-15 03:58 UTC
Run at homeGet help

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

Works with

Run2Convert3Scan1

Runs with

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

UltralyticsOpenVINO

Convert with

ONNXOptimumOlive

Scan with

ModelScan
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
5.82 GB
Weights
6.09 KB (smallest of 6 ONNX variants)
Parameters
not stated
Formats
onnx
Task
not tagged
License
MIT (permissive)
Files
30, 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 03:58 UTCpassed

Model card

From the publisher at commit d8d8eb5. Shown as plain text with links; images open at the publisher.

Phi-3 Vision-128k-Instruct ONNX models#

This repository hosts the optimized versions of Phi-3-vision-128k-instruct to accelerate inference with ONNX Runtime for your CPU and GPU.

Phi-3 Vision is a lightweight, state-of-the-art open multimodal model built upon datasets that include synthetic data and filtered publicly available web data with a focus on very high-quality, reasoning dense data both on text and vision. The model belongs to the Phi-3 model family, and the multimodal version supports up to 128K context length (in tokens). The base model has undergone a rigorous enhancement process, incorporating both supervised fine-tuning and direct preference optimization, to ensure precise instruction adherence and robust safety measures.

Optimized variants of the Phi-3 Vision models are published here in ONNX format to run with ONNX Runtime on CPU and GPU across devices, including server platforms, Windows, Linux and Mac desktops, and mobile CPUs, with the precision best suited to each of these targets.

ONNX Models#

Here are some of the optimized configurations we have added:

  1. ONNX model for INT4 CPU: ONNX model for CPUs using int4 quantization via RTN.
  2. ONNX model for INT4 GPU: ONNX model for GPUs using int4 quantization via RTN.

How to Get Started with the Model#

To support the Phi-3 models across a range of devices, platforms, and EP backends, we introduce a new API to wrap several aspects of generative AI inferencing. This API makes it easy to drag and drop LLMs straight into your app. To run the early version of these models with ONNX, follow the steps here.

Hardware Supported#

The models are tested on:

  • Intel(R) Core(TM) i9-10920X CPU @ 3.50GHz
  • 1 A100 GPU, SKU: Standard_ND96amsr_A100_v4 (CUDA)
  • GPU SKU: RTX 4080 (DirectML)

Minimum Configuration Required:

  • CPU machine with 16GB RAM
  • CUDA: NVIDIA GPU with Compute Capability >= 7.0
  • Windows: DirectX 12-capable GPU and a minimum of 10GB of combined RAM
Model Description#
  • Developed by: Microsoft
  • Model type: ONNX
  • Language(s) (NLP): Python, C, C++
  • License: MIT
  • Model Description: This is a conversion of the Phi-3 Vision-128K-Instruct model for ONNX Runtime inference.
  • Disclaimer: This 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. We have conducted responsible AI evaluations and did not observe significant regressions compared to the base model.

Additional Details#

Performance Metrics#

The performance of the ONNX vision model is similar to Phi-3-mini-128k-instruct-onnx during token generation.

Base Model Usage and Considerations#

For details and RAI considerations of the base model, please refer to here.

Please note that ONNX model output may vary slightly from the base model. The users are responsible for verifying the output for their scenarios and own responsibility of the usage.

Appendix#

Model Card Contact#

parinitarahi, kvaishnavi, natke, yunl, sunghcho

Contributors#

Kunal Vaishnavi, Sunghoon Choi, Yufeng Li, Baiju Meswani, Sheetal Arun Kadam, Rui Ren, Natalie Kershaw, Parinita Rahi, Patrice Vignola, Xiang Zhang, Chai Chaoweeraprasit, Logan Iyer, Vicente Rivera, Jacques Van Rhyn, Yun Liu

Trademarks#

This project may contain trademarks or logos for projects, products, or services. Authorized use of Microsoft trademarks or logos is subject to and must follow Microsoft’s Trademark & Brand Guidelines. Use of Microsoft trademarks or logos in modified versions of this project must not cause confusion or imply Microsoft sponsorship. Any use of third-party trademarks or logos are subject to those third-party’s policies.

Files

30 files · 5.82 GBWeights 6.09 KB (smallest of 6 ONNX variants). Sizes and sha256 from the signed manifest.
Show all 30 files with their sha256
FileSizesha256
.gitattributes1.57 KB1403a1a07764f40b81196144fc294c8daff49cbc0f1d0a79fcfbf5e35a027311
LICENSE1.08 KBfa8235e5b48faca34e3ca98cf4f694ef08bd216d28b58071a1f85b1d50cb814d
README.md4.76 KBcd138fd1ae9aac9c6f0a25d7c3fd6383632da36352cc14935214d7c9355706bc
config.json3.66 KBe3fbad3779524ca7e4186f276cd0fd81e2c2b33aaed3331fcced7253d5f7d391
cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4/genai_config.json2.13 KB32322df649fd863840d2dfd4589abf7c1f5aa23b999790a92ee5025f799d6992
cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4/phi-3-v-128k-instruct-embedding.onnx6.09 KB2adcc259530144da45e0b7b63312f3f6b166e2b610dac140c0bc979790819477
cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4/phi-3-v-128k-instruct-embedding.onnx.data394 MBf877b0c6f25857d655869226934d69384b1b8f26a8ccc938fc7b19ee0b178587
cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4/phi-3-v-128k-instruct-text.onnx52.1 MB9aa033f4b5fca5c17f4423e68c5bfc270780e69442705a215c22716676f66814
cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4/phi-3-v-128k-instruct-text.onnx.data2.33 GB48e242c6b8c99aeb78fd7195b815238aac4e4aef872c303d7366951c458c9b79
cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4/phi-3-v-128k-instruct-vision.onnx415 KBe1e78c5dc242c7855da7ae556222f8d1022cc55244b43872555e51d1079f88d4
cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4/phi-3-v-128k-instruct-vision.onnx.data445 MB327633e3c52c55b9f4e81a48c814465e30c970b82d2d6dd8af4e8a0357ff327d
cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4/processor_config.json821 Bd35a2862973f2adb6906df0274192f90b8666e08adac57e31db503d00528cabd
cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4/special_tokens_map.json670 Bf9535fada19315e0d8eb89521cebe111c008fee98d16e7c6744acfb50505d8c3
cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4/tokenizer.json1.85 MB478fb6fd0bf1403eb2ffda892e285f5ae968b9e0c06eb2815552ebedacb8ca93
cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4/tokenizer_config.json9.43 KB91352e5776a5feae7e85c64aba4a06eb724788b1862d920c8891acbc00e7011e
gpu/gpu-int4-rtn-block-32/genai_config.json2.13 KB32322df649fd863840d2dfd4589abf7c1f5aa23b999790a92ee5025f799d6992
gpu/gpu-int4-rtn-block-32/phi-3-v-128k-instruct-embedding.onnx6.09 KBc3d5accbf3767608c317ee239cabedc50427f3d8ac703e52de81f27759572af1
gpu/gpu-int4-rtn-block-32/phi-3-v-128k-instruct-embedding.onnx.data197 MBe22701dfc716f7e0f8b1938e1547b82e4cc39029cf9c8edb30416067190e0019
gpu/gpu-int4-rtn-block-32/phi-3-v-128k-instruct-text.onnx293 KBdb702d2d757a4ccbdbe2a52362a779157bd5654d5e1e7b7f77c19bd37c6ded2a
gpu/gpu-int4-rtn-block-32/phi-3-v-128k-instruct-text.onnx.data2.12 GBd07b7678bae20023a8db3dca5b1d020e0b4897bdf9124f5cd0a8b1805ee80b27
gpu/gpu-int4-rtn-block-32/phi-3-v-128k-instruct-vision.onnx423 KB5699fb72675887d6b7df81a41372d2d173228c23fe0259a3c12177da80fbb2b8
gpu/gpu-int4-rtn-block-32/phi-3-v-128k-instruct-vision.onnx.data282 MB326769ce2156a4b91a53ab127e570784aee824c15536cb0f6f9488ef74158475
gpu/gpu-int4-rtn-block-32/processor_config.json753 Bd99e46ad1153d648154b61a263f4dcbbbf95dfca342c6ac9c52dfa527f09a4a6
gpu/gpu-int4-rtn-block-32/special_tokens_map.json706 B8aa9f4bae46e5280787c8979252ffbf81f411a9aae79650f33a03d2a4b282514
gpu/gpu-int4-rtn-block-32/tokenizer.json1.85 MB478fb6fd0bf1403eb2ffda892e285f5ae968b9e0c06eb2815552ebedacb8ca93
gpu/gpu-int4-rtn-block-32/tokenizer_config.json9.84 KB9ae3df0010e39a598b2cae7222b06ac463a88a1d0aa4ba3d9f774c9d7174827d
onnx/builder.py8.10 KB4aa02d61e809497eb7353536c68a7ddc9a437e54b2f7228ce7473ddde784cdd7
onnx/config.json3.65 KB90a8c8ab1568392b75720b4a0c5a5751cb838154f8ce33d6b804e774794ec4f9
onnx/image_embedding_phi3_v.py20.2 KBb47fe43824d9a94d1e306c48f83e97e2bf58ef6e0eee26eb83f648c4be4295cf
onnx/modeling_phi3_v.py75.6 KBa40ea32ccaac939e61a9242afb35852d1ad8382a312dadc5ceee7353a33ff8d2
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
d8d8eb5e6e pinned now2026-11-15 03:58 UTC30 files · 5.82 GB

Use it

$ fw get microsoft/Phi-3-vision-128k-instruct-onnx
# manifest sha256 7c08ccc62c6f… · 5.82 GB · 30 files
$ fw verify ./Phi-3-vision-128k-instruct-onnx microsoft/Phi-3-vision-128k-instruct-onnx
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-vision-128k-instruct-onnx.json --dir ./Phi-3-vision-128k-instruct-onnx $ python3 fw.py verify ./Phi-3-vision-128k-instruct-onnx ./microsoft__Phi-3-vision-128k-instruct-onnx.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download microsoft/Phi-3-vision-128k-instruct-onnx --revision d8d8eb5e6e88e5068f6dd284300e1de6fc91ffbc --local-dir ./Phi-3-vision-128k-instruct-onnx
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
fa8235e5b48faca34e3ca98cf4f694ef08bd216d28b58071a1f85b1d50cb814d
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-vision-128k-instruct-onnxDate: 2026-11-15Commit: d8d8eb5Signed: 2DC28CC7B26A283B ✓
Upstream
microsoft/Phi-3-vision-128k-instruct-onnx
Pinned commit
d8d8eb5e6e88e5068f6dd284300e1de6fc91ffbc
Manifest
Phi-3-vision-128k-instruct-onnx.json · .minisig
Manifest sha256
7c08ccc62c6f52ebd7f4c2cb94eefeb6dc3e0e396a457a7ced32de306d4e982a
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 03:58 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/microsoft/Phi-3-vision-128k-instruct-onnx.json $ curl -O https://freeweights.allternit.com/manifests/microsoft/Phi-3-vision-128k-instruct-onnx.json.minisig $ minisign -Vm Phi-3-vision-128k-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

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-vision-128k-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. Phi-3-vision-128k-instruct-onnx.json. Provenance. Takedown history: none.
Source
huggingface.co/microsoft/Phi-3-vision-128k-instruct-onnx

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