What are the hardware requirements for Galactica 30B Evol Instruct 70K?

Galactica 30B Evol Instruct 70K requires approximately 60.1 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 Galactica 30B Evol Instruct 70K and how large is it?

Galactica 30B Evol Instruct 70K 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.

Where can I download or evaluate Galactica 30B Evol Instruct 70K?

Galactica 30B Evol Instruct 70K is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Galactica 30B Evol Instruct 70K by GeorgiaTechResearchInstitute — VRAM 60.1GB, 2K context

Name: Galactica 30B Evol Instruct 70K
Author: GeorgiaTechResearchInstitute

Galactica 30B Evol Instruct 70K is an open-source language model by GeorgiaTechResearchInstitute. Features: 30b LLM, VRAM: 60.1GB, Context: 2K, License: cc-by-nc-4.0, Instruction-Based, LLM Explorer Score: 0.07.

Arxiv:2304.12244 Alpaca Dataset:wizardlm/wizardlm evol... Galactica Instruct Opt Region:us Safetensors Sharded Tensorflow Wizardlm

Model Card on HF 🤗: https://huggingface.co/GeorgiaTechResearchInstitute/galactica-30b-evol-instruct-70k

Galactica 30B Evol Instruct 70K Parameters and Internals

Model Type

text generation

Use Cases

Areas:

scientific research

Primary Use Cases:

language model in scientific domain

Limitations:

potential to produce inaccurate information

Considerations:

Caution against production use without safeguards.

Additional Notes

Model is designed for scientific tasks.

Training Details

Data Sources:

scientific corpus, open-access scientific text, Evol-Instruct-70k dataset

Data Volume:

106 billion tokens

Methodology:

Fine-tuning using Evol-Instruct framework

Context Length:

1024

Training Time:

196 hours

Hardware Used:

16 A100 80GB GPUs

Input Output

Input Format:

Instruction-response

Accepted Modalities:

text

Output Format:

Text

LLM Name	Galactica 30B Evol Instruct 70K
Repository 🤗	https://huggingface.co/GeorgiaTechResearchInstitute/galactica-30b-evol-instruct-70k
Model Size	30b
Required VRAM	60.1 GB
Updated	2026-08-02
Maintainer	GeorgiaTechResearchInstitute
Model Type	opt
Instruction-Based	Yes
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 0.8 GB: 7-of-7
Model Architecture	OPTForCausalLM
License	cc-by-nc-4.0
Context Length	2048
Model Max Length	2048
Transformers Version	4.29.2
Tokenizer Class	PreTrainedTokenizerFast
Vocabulary Size	50000
Torch Data Type	bfloat16
Activation Function	gelu

Rank the Galactica 30B Evol Instruct 70K 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 Galactica 30B Evol Instruct 70K

Model	Likes	Downloads	VRAM
...ica 30B Evol Instruct 70K GPTQ	11	10	16 GB

Best Alternatives to Galactica 30B Evol Instruct 70K

Best Alternatives	Context / RAM	Downloads	Likes
...ica 30B Evol Instruct 70K GPTQ	2K / 16.3 GB	10	11