What are the hardware requirements for Kittylm Phi 4 Mini?

Kittylm Phi 4 Mini requires approximately 0.1 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Kittylm Phi 4 Mini and how large is it?

Kittylm Phi 4 Mini is developed by KittyLM, a model with 3.8b 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 Kittylm Phi 4 Mini?

Kittylm Phi 4 Mini is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Kittylm Phi 4 Mini by KittyLM — VRAM 0.1GB

Name: Kittylm Phi 4 Mini
Author: KittyLM

Kittylm Phi 4 Mini is an open-source language model by KittyLM. Features: 3.8b LLM, VRAM: 0.1GB, License: mit, Instruction-Based, LLM Explorer Score: 0.31.

Base model:adapter:microsoft/p... Base model:microsoft/phi-4-min... Conversational Custom code Dataset:kittylm/kittylm-data Endpoints compatible Instruct Kittylm Lora Persona Phi3 Region:us Roleplay Safetensors

Model Card on HF 🤗: https://huggingface.co/KittyLM/kittylm-phi-4-mini

Kittylm Phi 4 Mini Parameters and Internals

LLM Name	Kittylm Phi 4 Mini
Repository 🤗	https://huggingface.co/KittyLM/kittylm-phi-4-mini
Base Model(s)	Phi 4 Mini Instruct microsoft/Phi-4-mini-instruct
Model Size	3.8b
Required VRAM	0.1 GB
Updated	2026-10-01
Maintainer	KittyLM
Instruction-Based	Yes
Model Files	0.1 GB 7.7 GB
Model Architecture	AutoModelForCausalLM
License	mit
Model Max Length	131072
Is Biased	none
Tokenizer Class	GPT2Tokenizer
Padding Token	<\|endoftext\|>
PEFT Type	LORA
LoRA Model	Yes
PEFT Target Modules	gate_up_proj\|o_proj\|down_proj\|qkv_proj
LoRA Alpha	32
LoRA Dropout	0.05
R Param	32

Rank the Kittylm Phi 4 Mini 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 Kittylm Phi 4 Mini

Best Alternatives	Context / RAM	Downloads	Likes
Followup V6	0K / 7.6 GB	0	0
Phi 3 Mini Instruct 16bit	0K / 7.6 GB	6	0
...ct Bnb 4bit 16 4 100 1 Nonmath	0K / 7.6 GB	86	1