What are the hardware requirements for Phi 3 Mini 4K Instruct?

Phi 3 Mini 4K Instruct requires a context window of 4K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Phi 3 Mini 4K Instruct and how large is it?

Phi 3 Mini 4K Instruct is developed by Xenova. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Phi 3 Mini 4K Instruct?

Phi 3 Mini 4K Instruct is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Phi 3 Mini 4K Instruct by Xenova — 4K context

Name: Phi 3 Mini 4K Instruct
Author: Xenova

Phi 3 Mini 4K Instruct is an open-source language model by Xenova. Features: LLM, Context: 4K, License: mit, Instruction-Based, LLM Explorer Score: 0.13.

Conversational Dml Instruct Onnx Onnxruntime Phi3 Region:us Transformers.js

Model Card on HF 🤗: https://huggingface.co/Xenova/Phi-3-mini-4k-instruct

Phi 3 Mini 4K Instruct Parameters and Internals

Model Type

text-generation

Additional Notes

This is a version of the official phi3 onnx model with modifications for onnxruntime-web, including fp16 with int4 block quantization for weights, output in fp32, and using MHA instead of GQA. The onnx and external data file requirements are to be below 2GB for chromium caching.

LLM Name	Phi 3 Mini 4K Instruct
Repository 🤗	https://huggingface.co/Xenova/Phi-3-mini-4k-instruct
Updated	2026-08-04
Maintainer	Xenova
Model Type	phi3
Instruction-Based	Yes
Model Architecture	Phi3ForCausalLM
License	mit
Context Length	4096
Model Max Length	4096
Transformers Version	4.39.3
Tokenizer Class	LlamaTokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	32064
Torch Data Type	bfloat16

Rank the Phi 3 Mini 4K Instruct capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to Phi 3 Mini 4K Instruct

Best Alternatives	Context / RAM	Downloads	Likes
Phi 4 Mini Instruct ONNX GQA	128K / GB	47	6
Phi 3.5 Mini Instruct Onnx	128K / GB	138	39
Phi 3.5 Mini Instruct Onnx Web	128K / GB	407	15
Phi 3 Mini 128K Instruct Onnx	128K / GB	86	193
...i 3 Mini 128K Instruct Ov Int4	128K / 2 GB	8	0
...Medium 128K Instruct Onnx Cuda	128K / GB	82	24
... Medium 128K Instruct Onnx Cpu	128K / GB	84	14
...um 128K Instruct Onnx Directml	128K / GB	89	6
...3 Mini 128K Instruct Asym Int4	128K / 2.5 GB	122	0
Meeting Model Phi3 128k	128K / 7.7 GB	5	0

Note: green Score (e.g. "73.2") means that the model is better than Xenova/Phi-3-mini-4k-instruct.