Phi-3.5-mini-instruct-onnx ONNX download | Hugging Bay

Q: What is this model?

microsoft/Phi-3.5-mini-instruct-onnx is an open-weights language model for text generation published by microsoft, added to Hugging Bay Jun 30, 2026. Model from Hugging Face: microsoft/Phi-3.5-mini-instruct-onnx

Q: Can I use it commercially?

It is released under the mit license. Commercial use is allowed. Permissive open license: commercial use, modification, and redistribution are permitted.

Q: How big is it?

Hosted here: at least 15 listed files; full count and size unknown. The full repository size is not recorded. The recommended download, phi-3.5-mini-instruct-cpu-int4-awq-block-128-acc-level-4.onnx (AWQ), is 52.2 MB.

Q: What can I download here?

Hosted here: at least 15 listed files; full count and size unknown. Full repo upstream: unknown. The original release is at https://huggingface.co/microsoft/Phi-3.5-mini-instruct-onnx.

Q: File pattern scans

Automated file-pattern scans flagged nothing; not a safety guarantee. 15 hosted files carry a published SHA-256 you can re-hash. The machine-readable verdict is at /api/artifacts/hf-model-microsoft-phi-3-5-mini-instruct-onnx/safety on Hugging Bay.

Q: Will microsoft/Phi-3.5-mini-instruct-onnx run on my computer?

We can’t check the fit; we don’t know your machine. We don’t have your machine’s specs, so no check ran and no verdict is shown. Answer two quick questions and we’ll estimate, from the memory you tell us, whether it fits your machine. Or skip it; you can still download; fit isn’t checked.

microsoft

Phi-3.5-mini-instruct-onnx

Try browser chat with a small demo model (a separate model; device support is checked before loading).

microsoft/Phi-3.5-mini-instruct-onnx

Model details

text generationLicense: mitSHA-256 recorded for 15 of 22 filesONNX

Content controls: not assessed.

The catalog lists this model for having conversations. Catalog sources: license, tags, task.

View as JSON →

Your next step

Use it from code

This Python snippet downloads the selected file. Running the model needs its own library and setup.

from urllib.request import urlretrieve

urlretrieve(
    "https://huggingbay.xyz/api/downloads/hf-model-microsoft-phi-3-5-mini-instruct-onnx/cpu_and_mobile%2Fcpu-int4-awq-block-128-acc-level-4%2Fphi-3.5-mini-instruct-cpu-int4-awq-block-128-acc-level-4.onnx",
    "phi-3.5-mini-instruct-cpu-int4-awq-block-128-acc-level-4.onnx",
)

Other ways

This file cannot open in the app. The app supports one GGUF file at a time.

See app requirements

15 hosted of 22 listed · Hashes recorded. Date not recorded.

Selected downloadcpu_and_mobile/cpu-int4-awq-block-128-acc-level-4/phi-3.5-mini-instruct-cpu-int4-awq-block-128-acc-level-4.onnx52 MB · 1 file Download · 52 MB (1 file)

Open-file help

Content controls: not assessed.

Check your download →

Compare your file’s SHA-256 with the recorded hash.

15 hosted of 22 listed

Hashes recorded. Date not recorded.

File	Size	SHA-256	Source	Download
Weights
`cpu_and_mobile/cpu-int4-awq-block-128-acc-level-4/phi-3.5-mini-instruct-cpu-int4-awq-block-128-acc-level-4.onnx` Default	52.2 MB	`c4f05e6e…a10225fd` `c4f05e6ef52f2588df181e566afbf5e8eeba097fece2fc8246770473a10225fd`	Hosted	Download
`gpu/gpu-int4-awq-block-128/model.onnx`	26.2 MB	`c022f639…c0807ee7` `c022f639a6db4f0da6308e2f578fc698ac59c19a1976daee77783845c0807ee7`	Hosted	Download
Tokenizer & config
`config.json`	3.45 KB	`224de4f6…b5804974` `224de4f6a15b9d2a89695ec04b7f7ab2dd93a008a506979925e5a88cb5804974`	Hosted	Download
`cpu_and_mobile/cpu-int4-awq-block-128-acc-level-4/config.json`	3.45 KB	`224de4f6…b5804974` `224de4f6a15b9d2a89695ec04b7f7ab2dd93a008a506979925e5a88cb5804974`	Hosted	Download
`cpu_and_mobile/cpu-int4-awq-block-128-acc-level-4/genai_config.json`	1.58 KB	`d1036a44…b626f580` `d1036a44e904c816c864931b961483eccf18e985dbd6797eecb33e01b626f580`	Hosted	Download
`cpu_and_mobile/cpu-int4-awq-block-128-acc-level-4/tokenizer.json`	1.84 MB	`d0f067e1…0d474db7` `d0f067e1e15cd0a36ebef3668024882cb67a80b86fb4b7b4b128481f0d474db7`	Hosted	Download
`cpu_and_mobile/cpu-int4-awq-block-128-acc-level-4/tokenizer_config.json`	3.36 KB	`a12badd3…24f5f222` `a12badd3fb56adb29bc7cfe03cf6fa7e3e19dd3d7602b85ce6ed63d424f5f222`	Hosted	Download
`gpu/gpu-int4-awq-block-128/chat_template.jinja`	430 bytes	`78d976a4…89982a90` `78d976a442bcde2f0be15aafbb8e3050e1104f86732266f68403251b89982a90`	Hosted	Download
`gpu/gpu-int4-awq-block-128/config.json`	3.45 KB	`224de4f6…b5804974` `224de4f6a15b9d2a89695ec04b7f7ab2dd93a008a506979925e5a88cb5804974`	Hosted	Download
`gpu/gpu-int4-awq-block-128/genai_config.json`	1.53 KB	`4c54a6aa…b8662c1f` `4c54a6aa89532decf72fce0dae51b770a001d41bc32c31f5a39ba6f7b8662c1f`	Hosted	Download
`gpu/gpu-int4-awq-block-128/tokenizer.json`	3.62 MB	`3cb815b9…39300647` `3cb815b904d82b82b25dcd90edd00e71a5ee5443472ad611bcb84f1339300647`	Hosted	Download
`gpu/gpu-int4-awq-block-128/tokenizer_config.json`	2.93 KB	`78f1699f…9738f13c` `78f1699f672ba5c8c958fa9f69040560a0310967db88fcba80746d299738f13c`	Hosted	Download
`cpu_and_mobile/cpu-int4-awq-block-128-acc-level-4/special_tokens_map.json`	569 bytes	`474d6996…02313c34` `474d699677e264edd3851559548cbbb61801ad8da6b249c81455007602313c34`	Hosted	Download
`gpu/gpu-int4-awq-block-128/special_tokens_map.json`	569 bytes	`474d6996…02313c34` `474d699677e264edd3851559548cbbb61801ad8da6b249c81455007602313c34`	Hosted	Download
`configuration_phi3.py`	0 bytes	—	Upstream only	File metadata
`cpu_and_mobile/cpu-int4-awq-block-128-acc-level-4/configuration_phi3.py`	0 bytes	—	Upstream only	File metadata
`cpu_and_mobile/cpu-int4-awq-block-128-acc-level-4/phi-3.5-mini-instruct-cpu-int4-awq-block-128-acc-level-4.onnx.data`	0 bytes	—	Upstream only	File metadata
`gpu/gpu-int4-awq-block-128/configuration_phi3.py`	0 bytes	—	Upstream only	File metadata
`gpu/gpu-int4-awq-block-128/model.onnx.data`	0 bytes	—	Upstream only	File metadata
Docs
`README.md`	12.2 KB	`f0376b37…62dff374` `f0376b376200ad6fb2f6e7c7f9ef5546c1b530b599707779e1db84eb62dff374`	Hosted	Download
`.gitattributes`	0 bytes	—	Upstream only	File metadata
`LICENSE`	0 bytes	—	Upstream only	File metadata

Check a download

In the folder where you saved phi-3.5-mini-instruct-cpu-int4-awq-block-128-acc-level-4.onnx, run:

macOS

shasum -a 256 -- 'phi-3.5-mini-instruct-cpu-int4-awq-block-128-acc-level-4.onnx'

Linux

sha256sum -- 'phi-3.5-mini-instruct-cpu-int4-awq-block-128-acc-level-4.onnx'

Windows

Get-FileHash -LiteralPath 'phi-3.5-mini-instruct-cpu-int4-awq-block-128-acc-level-4.onnx' -Algorithm SHA256

Compare the result with the recorded SHA-256.

Phi-3.5-mini-instruct-onnx

Check a download

Cookies