What are the hardware requirements for Phi 2 Ov Quantized?

Phi 2 Ov Quantized requires approximately 1.9 GB of VRAM and supports a context window of 2K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Phi 2 Ov Quantized and how large is it?

Phi 2 Ov Quantized is developed by Intel. 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 2 Ov Quantized?

Phi 2 Ov Quantized is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Phi 2 Ov Quantized by Intel — VRAM 1.9GB, 2K context

Name: Phi 2 Ov Quantized
Author: Intel

Phi 2 Ov Quantized is an open-source language model by Intel. Features: LLM, VRAM: 1.9GB, Context: 2K, License: mit, LLM Explorer Score: 0.12.

Code En Endpoints compatible Openvino Phi Region:us

Model Card on HF 🤗: https://huggingface.co/Intel/phi-2-ov-quantized

Phi 2 Ov Quantized Parameters and Internals

Model Type

Transformer-based, text-generation

Use Cases

Areas:

Research, Commercial applications

Primary Use Cases:

QA Format, Chat Format, Code Format

Limitations:

Generate Inaccurate Code and Facts, Limited Scope for code, Unreliable Responses to Instruction, Language Limitations, Potential Societal Biases, Toxicity, Verbosity

Considerations:

Users should treat generated content as starting points and verify all outputs, especially in unfamiliar contexts.

Supported Languages

English (standard)

Training Details

Data Sources:

NLP synthetic texts, filtered websites

Model Architecture:

Transformer

LLM Name	Phi 2 Ov Quantized
Repository 🤗	https://huggingface.co/Intel/phi-2-ov-quantized
Required VRAM	1.9 GB
Updated	2026-07-26
Maintainer	Intel
Model Type	phi
Model Files	1.9 GB
Supported Languages	en
Model Architecture	PhiForCausalLM
License	mit
Context Length	2048
Model Max Length	2048
Transformers Version	4.37.0
Tokenizer Class	CodeGenTokenizer
Vocabulary Size	51200
Torch Data Type	float16

Rank the Phi 2 Ov Quantized 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

Quantized Models of the Phi 2 Ov Quantized

Model	Likes	Downloads	VRAM
Phi 2 Quantized	11	114	1 GB

Best Alternatives to Phi 2 Ov Quantized

Best Alternatives	Context / RAM	Downloads	Likes
Merlin1.4	2K / 5.6 GB	74	0
Merlin1.5	2K / 5.6 GB	99	0
Merlin1.2	2K / 5.6 GB	65	0
Merlin1.3	2K / 5.6 GB	67	0
Phi1.5 Quantized 2	2K / GB	5	0
Tinyllama Quant	2K / 0.8 GB	6	1
Phi1.5 Update 4	2K / GB	6	0
Phi 2 Fp8	2K / 3.3 GB	89	0
Phi Medquad Frequency	2K / 5.6 GB	5	0
Phi 2 Fp8	2K / 3.3 GB	7	0

Note: green Score (e.g. "73.2") means that the model is better than Intel/phi-2-ov-quantized.