What are the hardware requirements for Galpaca 30B?

Galpaca 30B requires approximately 60.8 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 Galpaca 30B and how large is it?

Galpaca 30B is developed by GeorgiaTechResearchInstitute, 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 Galpaca 30B perform on standard benchmarks?

Galpaca 30B has the following published scores: MMLU 43.78. Compare against reference models on this page or on the LLM Explorer leaderboards.

Galpaca 30B by GeorgiaTechResearchInstitute — VRAM 60.8GB, 2K context

Name: Galpaca 30B
Author: GeorgiaTechResearchInstitute

Galpaca 30B is an open-source language model by GeorgiaTechResearchInstitute. Features: 30b LLM, VRAM: 60.8GB, Context: 2K, License: cc-by-nc-4.0, LLM Explorer Score: 0.1, Arc: 49.6, HellaSwag: 58.2, MMLU: 43.8, GSM8K: 2.8.

Alpaca Dataset:tatsu-lab/alpaca Galactica Opt Pytorch Region:us Sharded

Model Card on HF 🤗: https://huggingface.co/GeorgiaTechResearchInstitute/galpaca-30b

Galpaca 30B Parameters and Internals

Model Type

text-generation

Use Cases

Areas:

Research on language models applied to the scientific domain

Primary Use Cases:

Scientific task performance, Instruction-following capability enhancement

Limitations:

Not recommended for production use without safeguards due to potential inaccuracies

Considerations:

Potential to produce inaccurate information.

Training Details

Data Sources:

Open-access scientific text and data, Alpaca dataset consisting of 52k instruct-response pairs

Data Volume:

106 billion tokens

Methodology:

Fine-tuned on the Alpaca dataset

Context Length:

384

Training Time:

6 hours

Hardware Used:

16 A100 80GB GPUs

Model Architecture:

Fine-tuned variant of a pre-trained GALACTICA model using DeepSpeed ZeRO Stage 3.

Input Output

Input Format:

Instruction-based prompts

Accepted Modalities:

text

Output Format:

Text completion

LLM Name	Galpaca 30B
Repository 🤗	https://huggingface.co/GeorgiaTechResearchInstitute/galpaca-30b
Model Size	30b
Required VRAM	60.8 GB
Updated	2026-08-04
Maintainer	GeorgiaTechResearchInstitute
Model Type	opt
Model Files	9.8 GB: 1-of-7 9.9 GB: 2-of-7 9.9 GB: 3-of-7 9.9 GB: 4-of-7 9.9 GB: 5-of-7 9.9 GB: 6-of-7 1.5 GB: 7-of-7
Model Architecture	OPTForCausalLM
License	cc-by-nc-4.0
Context Length	2048
Model Max Length	2048
Transformers Version	4.28.0.dev0
Tokenizer Class	PreTrainedTokenizerFast
Vocabulary Size	50000
Torch Data Type	float16
Activation Function	gelu

Rank the Galpaca 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

Best Alternatives to Galpaca 30B

Best Alternatives	Context / RAM	Downloads	Likes
Galpaca 30B MiniOrca	2K / 59.6 GB	48	1
Opt 30B	2K / 60.1 GB	14167	137
Opt Iml Max 30B	2K / 60.1 GB	1150	35
OPT 30B Erebus	2K / 36 GB	60	67
...alactica 30B Evol Instruct 70K	2K / 60.1 GB	57	23
Opt Iml 30B	2K / 60.1 GB	36	73
Galactica 30B	2K / 60.8 GB	71	40
Dalio Io 30B Cp1500	2K / 121.7 GB	11	0
Galactica 30B	2K / GB	19	1
...h 1e 5 Lr Handwritten Complete	2K / 121.7 GB	18	0

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