What are the hardware requirements for Phi 3 Mini 128K Instruct 4bit 64rank?

Phi 3 Mini 128K Instruct 4bit 64rank requires approximately 2.4 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 Mini 128K Instruct 4bit 64rank and how large is it?

Phi 3 Mini 128K Instruct 4bit 64rank is developed by LoftQ, a model with 3.9b 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 Mini 128K Instruct 4bit 64rank?

Phi 3 Mini 128K Instruct 4bit 64rank is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Phi 3 Mini 128K Instruct 4bit 64rank by LoftQ — VRAM 2.4GB, 128K context

Name: Phi 3 Mini 128K Instruct 4bit 64rank
Author: LoftQ

Phi 3 Mini 128K Instruct 4bit 64rank is an open-source language model by LoftQ. Features: 3.9b LLM, VRAM: 2.4GB, Context: 128K, License: mit, Quantized, Instruction-Based, LLM Explorer Score: 0.12.

Arxiv:2310.08659 4-bit 4bit Bitsandbytes Conversational Custom code En Endpoints compatible Instruct Lora Phi3 Quantization Quantized Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/LoftQ/Phi-3-mini-128k-instruct-4bit-64rank

Phi 3 Mini 128K Instruct 4bit 64rank Parameters and Internals

Model Type

text-generation

Additional Notes

Model supports LoRA fine-tuning with adapters and quantized backbone.

Supported Languages

en (proficient)

LLM Name	Phi 3 Mini 128K Instruct 4bit 64rank
Repository 🤗	https://huggingface.co/LoftQ/Phi-3-mini-128k-instruct-4bit-64rank
Model Size	3.9b
Required VRAM	2.4 GB
Updated	2026-08-02
Maintainer	LoftQ
Model Type	phi3
Instruction-Based	Yes
Model Files	2.4 GB
Supported Languages	en
Quantization Type	4bit
Model Architecture	Phi3ForCausalLM
License	mit
Context Length	131072
Model Max Length	131072
Transformers Version	4.40.1
Tokenizer Class	LlamaTokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	32064
LoRA Model	Yes
Torch Data Type	bfloat16

Rank the Phi 3 Mini 128K Instruct 4bit 64rank 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 3 Mini 128K Instruct 4bit 64rank

Model	Likes	Downloads	VRAM
NaturalLanguagePioneersSTEMExp	0	5	0 GB

Best Alternatives to Phi 3 Mini 128K Instruct 4bit 64rank

Best Alternatives	Context / RAM	Downloads	Likes
...Mini Instruct Unsloth Bnb 4bit	128K / 3.2 GB	6780	22
Phi 4 Mini Instruct Bnb 4bit	128K / 2.9 GB	6866	6
Phi 4 Mini Instruct Bnb 4bit	128K / 2.9 GB	5	0
...hi 3 Medium 128K Instruct 8bit	128K / 14.9 GB	18	2
... 3 Mini 128K Instruct Bnb 4bit	128K / 2.3 GB	7	1
Phi 3 Medium 4K Instruct 8bit	4K / 14.9 GB	8	0
...3 Mini 4K Instruct 4bit 64rank	4K / 2.4 GB	7	0
Phi 3 Mini 4K Instruct Q4	4K / 2.3 GB	6	1
...hi 3 Mini 4K Instruct Bnb 4bit	4K / 2.3 GB	19	6
...hi 3 Mini 4K Instruct Bnb 4bit	4K / 2.3 GB	7	0

Note: green Score (e.g. "73.2") means that the model is better than LoftQ/Phi-3-mini-128k-instruct-4bit-64rank.