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

Phi 3 Mini 4K Python requires approximately 7.6 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

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

Phi 3 Mini 4K Python is developed by theprint. 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 Python?

Phi 3 Mini 4K Python 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 Python by theprint — VRAM 7.6GB

Name: Phi 3 Mini 4K Python
Author: theprint

Phi 3 Mini 4K Python is an open-source language model by theprint. Features: LLM, VRAM: 7.6GB, License: apache-2.0, Quantized, Instruction-Based, LLM Explorer Score: 0.18.

4bit Base model:quantized:unsloth/p... Base model:unsloth/phi-3-mini-... Conversational Dataset:ajibawa-2023/python-co... Dataset:iamtarun/python code i... En Endpoints compatible Gguf Instruct Lora Mistral Model-index Pytorch Quantized Region:us Safetensors Sft Sharded Trl Unsloth

Model Card on HF 🤗: https://huggingface.co/theprint/phi-3-mini-4k-python

Phi 3 Mini 4K Python Parameters and Internals

Model Type

text-generation-inference, transformers, unsloth, mistral, trl, sft

Additional Notes

This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.

LLM Name	Phi 3 Mini 4K Python
Repository 🤗	https://huggingface.co/theprint/phi-3-mini-4k-python
Base Model(s)	...hi 3 Mini 4K Instruct Bnb 4bit unsloth/Phi-3-mini-4k-instruct-bnb-4bit
Required VRAM	7.6 GB
Updated	2026-08-06
Maintainer	theprint
Instruction-Based	Yes
Model Files	0.1 GB 7.6 GB 2.3 GB 2.7 GB 3.1 GB 4.1 GB 5.0 GB: 1-of-2 2.6 GB: 2-of-2
Supported Languages	en
GGUF Quantization	Yes
Quantization Type	4bit\|gguf
Model Architecture	AutoModelForCausalLM
License	apache-2.0
Model Max Length	131072
Is Biased	none
Tokenizer Class	LlamaTokenizer
Padding Token	<\|placeholder6\|>
PEFT Type	LORA
LoRA Model	Yes
PEFT Target Modules	k_proj\|o_proj\|gate_proj\|q_proj\|up_proj\|down_proj\|v_proj
LoRA Alpha	32
LoRA Dropout	0
R Param	16

Rank the Phi 3 Mini 4K Python 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 Python

Best Alternatives	Context / RAM	Downloads	Likes
Pipi	0K / 2.4 GB	13	0
...emo Instruct 2407 EXL2 8bpw H8	0K / 12.6 GB	7	7
Dre Phi	0K / 7.6 GB	7	0
Phi 3 Mini 4K CodeInstruct	0K / 7.6 GB	10	0
...3 Mini 4K Instruct Text To Sql	0K / 7.6 GB	12	0
VLM2Vec LoRA	0K / 0 GB	96	11
... Mini 4K Instruct Chinese Lora	0K / 0 GB	8	6
Falcon Camel Math Instruct	0K / 0 GB	2	1
Instruct Igel 001	0K / 12.9 GB	13	47