What are the hardware requirements for VicUnlocked Alpaca 30B?

VicUnlocked Alpaca 30B requires approximately 65.2 GB of VRAM and supports a context window of 2K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

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

VicUnlocked Alpaca 30B 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.

How does VicUnlocked Alpaca 30B perform on standard benchmarks?

VicUnlocked Alpaca 30B has the following published scores: MMLU 57.64. Compare against reference models on this page or on the LLM Explorer leaderboards.

VicUnlocked Alpaca 30B by Aeala — VRAM 65.2GB, 2K context

Name: VicUnlocked Alpaca 30B
Author: Aeala

VicUnlocked Alpaca 30B is an open-source language model by Aeala. Features: 30b LLM, VRAM: 65.2GB, Context: 2K, LLM Explorer Score: 0.09, Arc: 61.9, HellaSwag: 83.8, MMLU: 57.6, GSM8K: 14.6.

Endpoints compatible Llama Pytorch Region:us Safetensors Sharded Tensorflow

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

VicUnlocked Alpaca 30B Parameters and Internals

Model Type

text generation

Use Cases

Areas:

research

Additional Notes

Model is designed for use with Alpaca instruction format.

Training Details

Data Sources:

cleaned ShareGPT dataset

Methodology:

Trained in Alpaca format

Model Architecture:

LoRA

Input Output

Input Format:

### Instruction: ### Response:

Accepted Modalities:

text

Output Format:

text

Performance Tips:

Use the Alpaca format for best results.

LLM Name	VicUnlocked Alpaca 30B
Repository 🤗	https://huggingface.co/Aeala/VicUnlocked-alpaca-30b
Model Size	30b
Required VRAM	65.2 GB
Updated	2026-09-04
Maintainer	Aeala
Model Type	llama
Model Files	9.8 GB: 1-of-7 10.0 GB: 2-of-7 9.9 GB: 3-of-7 9.9 GB: 4-of-7 9.9 GB: 5-of-7 10.0 GB: 6-of-7 5.7 GB: 7-of-7 9.8 GB: 1-of-7 10.0 GB: 2-of-7 9.9 GB: 3-of-7 9.9 GB: 4-of-7 9.9 GB: 5-of-7 10.0 GB: 6-of-7 5.9 GB: 7-of-7
Model Architecture	LlamaForCausalLM
Context Length	2048
Model Max Length	2048
Transformers Version	4.29.0
Tokenizer Class	LlamaTokenizer
Beginning of Sentence Token	<s>
End of Sentence Token	</s>
Unk Token	<unk>
Vocabulary Size	32000
Torch Data Type	float16

Rank the VicUnlocked Alpaca 30B 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 VicUnlocked Alpaca 30B

Model	Likes	Downloads	VRAM
VicUnlocked Alpaca 30B 4bit	5	20	16 GB

Best Alternatives to VicUnlocked Alpaca 30B

Best Alternatives	Context / RAM	Downloads	Likes
TildeOpen 30B	64K / 60.9 GB	4576	165
TildeOpen 30B 64K	64K / 60.9 GB	702	3
Tildeopen 30B Mu Instruct	64K / 60.9 GB	41	6
Flash Llama 30M 20001	32K / 0.1 GB	134	0
Smaug Slerp 30B V0.1	32K / 60.4 GB	79	0
Tenebra 30B Alpha01	16K / 65 GB	50	16
Llama33b 16K	16K / 65.2 GB	1	1
Veyra2 Mango 30M Base	4K / 0.1 GB	0	5
Yayi2 30B Llama	4K / 121.2 GB	922	22
... Tokens By Perplexity Bottom K	4K / 5.4 GB	8	0

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