What are the hardware requirements for VicUnlocked Alpaca Half 30B LoRA?

VicUnlocked Alpaca Half 30B LoRA requires approximately 0.2 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed VicUnlocked Alpaca Half 30B LoRA and how large is it?

VicUnlocked Alpaca Half 30B LoRA is developed by Aeala, a model with 30b 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 VicUnlocked Alpaca Half 30B LoRA?

VicUnlocked Alpaca Half 30B LoRA is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

VicUnlocked Alpaca Half 30B LoRA by Aeala — VRAM 0.2GB

Name: VicUnlocked Alpaca Half 30B LoRA
Author: Aeala

VicUnlocked Alpaca Half 30B LoRA is an open-source language model by Aeala. Features: 30b LLM, VRAM: 0.2GB, LLM Explorer Score: 0.07.

Adapter Dataset:aeala/sharegpt vicuna ... Finetuned Lora Region:us

Model Card on HF 🤗: https://huggingface.co/Aeala/VicUnlocked-alpaca-half-30b-LoRA

VicUnlocked Alpaca Half 30B LoRA Parameters and Internals

Model Type

LoRA

Additional Notes

This is a highly experimental model with mixed results. Trained for 3 epochs with checkpoint uploads at 2.97 and 0.8 epochs.

Training Details

Data Sources:

Aeala/ShareGPT_Vicuna_unfiltered

Methodology:

Trained in the Alpaca format

LLM Name	VicUnlocked Alpaca Half 30B LoRA
Repository 🤗	https://huggingface.co/Aeala/VicUnlocked-alpaca-half-30b-LoRA
Model Size	30b
Required VRAM	0.2 GB
Updated	2026-08-13
Maintainer	Aeala
Model Files	0.2 GB
Model Architecture	Adapter
Is Biased	none
PEFT Type	LORA
LoRA Model	Yes
PEFT Target Modules	q_proj\|k_proj\|v_proj\|o_proj
LoRA Alpha	32
LoRA Dropout	0.05
R Param	16

Rank the VicUnlocked Alpaca Half 30B LoRA 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 VicUnlocked Alpaca Half 30B LoRA

Best Alternatives	Context / RAM	Downloads	Likes
...3.5 30B A3B Antislop FTPO LoRA	0K / 0.8 GB	7	1
...ans PersonalityEngine 30B LoRA	0K / 0.2 GB	0	1
...ans PersonalityEngine 30B LoRA	0K / 0.2 GB	0	1
SoTana 30B Lora 500000	0K / 0.1 GB	0	1
Gpt4 Alpaca Lora 30B	0K / 0.2 GB	0	64
Saiga 30b Lora	0K / 0.2 GB	0	23
Tianpeng Lora 30B	0K / 0.2 GB	0	7
Baize Lora 30B	0K / 0.2 GB	0	34
Alpaca Lora 30B	0K / 0.2 GB	0	49
KoAlpaca 30B LoRA	0K / 0.1 GB	0	4

Note: green Score (e.g. "73.2") means that the model is better than Aeala/VicUnlocked-alpaca-half-30b-LoRA.