What are the hardware requirements for Phi 3 Medium 128K Instruct Onnx Cuda?

Phi 3 Medium 128K Instruct Onnx Cuda requires a context window of 128K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Phi 3 Medium 128K Instruct Onnx Cuda and how large is it?

Phi 3 Medium 128K Instruct Onnx Cuda is developed by microsoft. 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 Medium 128K Instruct Onnx Cuda?

Phi 3 Medium 128K Instruct Onnx Cuda is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Phi 3 Medium 128K Instruct Onnx Cuda by microsoft — 128K context

Name: Phi 3 Medium 128K Instruct Onnx Cuda
Author: microsoft

Phi 3 Medium 128K Instruct Onnx Cuda is an open-source language model by microsoft. Features: LLM, Context: 128K, License: mit, Instruction-Based, LLM Explorer Score: 0.13.

Conversational Custom code Dml Instruct Onnx Onnxruntime Phi3 Region:us

Model Card on HF 🤗: https://huggingface.co/microsoft/Phi-3-medium-128k-instruct-onnx-cuda

Phi 3 Medium 128K Instruct Onnx Cuda Parameters and Internals

Model Type

text generation, conversational, nlp

Use Cases

Areas:

research, commercial applications

Supported Languages

Python (full proficiency), C (support), C++ (support)

Training Details

Data Sources:

Phi-3 datasets, synthetic data, filtered publicly available websites

Methodology:

supervised fine-tuning, direct preference optimization

Context Length:

128000

Input Output

Accepted Modalities:

text

LLM Name	Phi 3 Medium 128K Instruct Onnx Cuda
Repository 🤗	https://huggingface.co/microsoft/Phi-3-medium-128k-instruct-onnx-cuda
Updated	2026-08-01
Maintainer	microsoft
Model Type	phi3
Instruction-Based	Yes
Model Architecture	Phi3ForCausalLM
License	mit
Context Length	131072
Model Max Length	131072
Transformers Version	4.39.3
Vocabulary Size	32064
Torch Data Type	bfloat16

Rank the Phi 3 Medium 128K Instruct Onnx Cuda 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 Medium 128K Instruct Onnx Cuda

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 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
Model1	128K / 0.8 GB	20	0

Note: green Score (e.g. "73.2") means that the model is better than microsoft/Phi-3-medium-128k-instruct-onnx-cuda.