llmware/phi-3-mini-4k-instruct-onnx-qnn

By llmware · ↓ 7 · ♥ 0 · Updated 2025-12-20

What's in this repo

This page lists the files in llmware/phi-3-mini-4k-instruct-onnx-qnn, including context_ctx.onnx, embeddings.onnx, iterator_ctx.onnx and more.

4 ONNX models (.onnx files)
23 files, including 9 .json, 4 .bin, 4 .onnx, 2 .py, 1 .md, 1 .jinja
Last updated 2025-12-20

ONNX files

File	Size	Download
context_ctx.onnx	—	Download
embeddings.onnx	—	Download
iterator_ctx.onnx	—	Download
lm_head.onnx	—	Download

How to use

These ONNX files can be loaded with ONNX Runtime. To inspect a model graph, upload the file to the Netron viewer. Download links point to the original files on Hugging Face.

README

phi-3-mini-4k-onnx-qnn

phi-3-mini-4k-onnx-qnn is an ONNX QNN int4 quantized version of Microsoft Phi-3-mini-instruct, providing a small fast NPU inference implementation, optimized for NPU deployment on Windows ARM64 AI PCs with Snapdragon Elite X NPU processors.

Model Description

Developed by: microsoft
Model type: phi3
Parameters: 3.8 billion
Model Parent: microsoft/Phi-3-mini-instruct
Language(s) (NLP): English
License: Apache 2.0
Uses: Chat, general-purpose LLM
Quantization: int4
Backend: qairt 2.36, ort 1.22.2, ortg 0.9

Model Card Contact

llmware on hf

llmware website

Model info

onnx phi3 green llmware-chat p3 qnn emerald custom_code license:apache-2.0 4-bit gptq region:us

↓ 7 ♥ 0

Created: 2025-12-20

Updated: 2025-12-20

View on Hugging Face

Files (23)

.gitattributes

README.md

added_tokens.json

chat_template.jinja

config.json

configuration_phi3.py

context_0_ctx_qnn.bin

context_1_ctx_qnn.bin

context_2_ctx_qnn.bin

context_3_ctx_qnn.bin

context_ctx.onnx ONNX

embeddings.onnx ONNX

genai_config.json

generation_config.json

hash_record_sha256.json

inference_model.json

iterator_ctx.onnx ONNX

lm_head.onnx ONNX

modeling_phi3.py

special_tokens_map.json

tokenizer.json

tokenizer.model

tokenizer_config.json

Related models

More models

No task type declared.