What are the hardware requirements for Phi 3 Vision 128K Instruct 4bit?

Phi 3 Vision 128K Instruct 4bit requires approximately 2.3 GB of VRAM and supports 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 Vision 128K Instruct 4bit and how large is it?

Phi 3 Vision 128K Instruct 4bit is developed by mlx-community, a model with 648.9m parameters. 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 Vision 128K Instruct 4bit?

Phi 3 Vision 128K Instruct 4bit is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Phi 3 Vision 128K Instruct 4bit by mlx-community — VRAM 2.3GB, 128K context

Name: Phi 3 Vision 128K Instruct 4bit
Author: mlx-community

Phi 3 Vision 128K Instruct 4bit is an open-source language model by mlx-community. Features: 648.9m LLM, VRAM: 2.3GB, Context: 128K, License: mit, Quantized, Instruction-Based, LLM Explorer Score: 0.13.

4bit Code Conversational Custom code Instruct Mlx Multilingual Phi3 v Quantized Region:us Safetensors Vision

Model Card on HF 🤗: https://huggingface.co/mlx-community/Phi-3-vision-128k-instruct-4bit

Phi 3 Vision 128K Instruct 4bit Parameters and Internals

Model Type

nlp, code, vision

Additional Notes

This model was converted to MLX format from `microsoft/Phi-3-vision-128k-instruct` using mlx-vlm version 0.0.10.

Supported Languages

multilingual ()

LLM Name	Phi 3 Vision 128K Instruct 4bit
Repository 🤗	https://huggingface.co/mlx-community/Phi-3-vision-128k-instruct-4bit
Model Size	648.9m
Required VRAM	2.3 GB
Updated	2026-08-08
Maintainer	mlx-community
Model Type	phi3_v
Instruction-Based	Yes
Model Files	2.3 GB
Quantization Type	4bit
Model Architecture	Phi3VForCausalLM
License	mit
Context Length	131072
Model Max Length	131072
Transformers Version	4.38.1
Tokenizer Class	LlamaTokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	32064
Torch Data Type	bfloat16

Rank the Phi 3 Vision 128K Instruct 4bit 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 Vision 128K Instruct 4bit

Best Alternatives	Context / RAM	Downloads	Likes
Phi 3.5 Vision Instruct 4bit	128K / 2.3 GB	211	6

Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Phi-3-vision-128k-instruct-4bit.