What are the hardware requirements for VicUnlocked Alpaca 65B QLoRA?

VicUnlocked Alpaca 65B QLoRA requires approximately 1.6 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed VicUnlocked Alpaca 65B QLoRA and how large is it?

VicUnlocked Alpaca 65B QLoRA is developed by Aeala, a model with 65b 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 65B QLoRA?

VicUnlocked Alpaca 65B QLoRA is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

VicUnlocked Alpaca 65B QLoRA by Aeala — VRAM 1.6GB

Name: VicUnlocked Alpaca 65B QLoRA
Author: Aeala

VicUnlocked Alpaca 65B QLoRA is an open-source language model by Aeala. Features: 65b LLM, VRAM: 1.6GB, LLM Explorer Score: 0.07.

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

Model Card on HF 🤗: https://huggingface.co/Aeala/VicUnlocked-alpaca-65b-QLoRA

VicUnlocked Alpaca 65B QLoRA Parameters and Internals

Additional Notes

Highly experimental model. Training is currently paused.

Training Details

Data Sources:

Aeala/ShareGPT_Vicuna_unfiltered

Methodology:

Trained in the Alpaca format with a cleaned ShareGPT dataset, retrain at ~1000 steps using fixed QLoRA repo.

Input Output

Input Format:

### Instruction: <instruction> ### Response:

Release Notes

Version:

retrain ~1000 steps

Date:

6/4/2023

Notes:

Checkpoint of a retrain with fixed QLoRA repo.

LLM Name	VicUnlocked Alpaca 65B QLoRA
Repository 🤗	https://huggingface.co/Aeala/VicUnlocked-alpaca-65b-QLoRA
Model Size	65b
Required VRAM	1.6 GB
Updated	2026-10-21
Maintainer	Aeala
Model Files	1.6 GB
Model Architecture	Adapter
Is Biased	none
PEFT Type	LORA
LoRA Model	Yes
PEFT Target Modules	gate_proj\|q_proj\|down_proj\|v_proj\|o_proj\|k_proj\|up_proj
LoRA Alpha	16
LoRA Dropout	0.05
R Param	64

Rank the VicUnlocked Alpaca 65B QLoRA 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 65B QLoRA

Best Alternatives	Context / RAM	Downloads	Likes
Airoboros 65B Gpt4 1.4 Peft	0K / 1.6 GB	12	0
Alpaca Lora 65B En Pt Es Ca	0K / 0.1 GB	0	2
...os 65B Gpt4 1.4.1 PI 8192 Peft	0K / 1.6 GB	0	1
Enterredaas 65B QLoRA	0K / 1.6 GB	0	4
Saiga 65b Lora	0K / 0.3 GB	0	6
Guanaco 65B	0K / 3.2 GB	0	88
Qlora Self Instruct 65B	0K / 3.2 GB	0	2
Qlora Flan 65B	0K / 3.2 GB	0	1
Alpaca Lora 65B	0K / 0.1 GB	0	25
Alpaca 65B	0K / 0.1 GB	0	17

Note: green Score (e.g. "73.2") means that the model is better than Aeala/VicUnlocked-alpaca-65b-QLoRA.