What are the hardware requirements for Polyglot Ko 12.8B Instruct?

Polyglot Ko 12.8B Instruct requires approximately 0.2 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 Polyglot Ko 12.8B Instruct and how large is it?

Polyglot Ko 12.8B Instruct is developed by etri-xainlp, a model with 12.8b 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 Polyglot Ko 12.8B Instruct?

Polyglot Ko 12.8B Instruct is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Polyglot Ko 12.8B Instruct by etri-xainlp — VRAM 0.2GB, 2K context

Name: Polyglot Ko 12.8B Instruct
Author: etri-xainlp

Polyglot Ko 12.8B Instruct is an open-source language model by etri-xainlp. Features: 12.8b LLM, VRAM: 0.2GB, Context: 2K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.09.

Endpoints compatible Gpt neox Instruct Ko Pytorch Region:us

Model Card on HF 🤗: https://huggingface.co/etri-xainlp/polyglot-ko-12.8b-instruct

Polyglot Ko 12.8B Instruct Parameters and Internals

Model Type

Instruction-based, Text generation

Additional Notes

Model trained with Adam optimizer, linear learning rate scheduler.

Supported Languages

Korean (High)

Training Details

Data Sources:

Instruction-following dataset (260k)

Methodology:

Fine-tuning

Hardware Used:

multi-GPU(A100 80G)

Input Output

Input Format:

text prompts

Accepted Modalities:

text

Output Format:

generated text

Performance Tips:

Use distributed multi-GPU setup for optimal performance.

LLM Name	Polyglot Ko 12.8B Instruct
Repository 🤗	https://huggingface.co/etri-xainlp/polyglot-ko-12.8b-instruct
Model Size	12.8b
Required VRAM	0.2 GB
Updated	2026-08-05
Maintainer	etri-xainlp
Model Type	gpt_neox
Instruction-Based	Yes
Model Files	26.0 GB 0.0 GB 0.2 GB 19.3 GB 0.2 GB 19.3 GB 0.2 GB 19.3 GB 0.2 GB 19.3 GB 0.2 GB 19.3 GB 0.2 GB 19.3 GB 0.2 GB 19.3 GB 0.2 GB 19.3 GB
Supported Languages	ko
Model Architecture	GPTNeoXForCausalLM
License	apache-2.0
Context Length	2048
Model Max Length	2048
Transformers Version	4.30.2
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<\|endoftext\|>
Vocabulary Size	30003
Torch Data Type	float16

Rank the Polyglot Ko 12.8B Instruct 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 Polyglot Ko 12.8B Instruct

Best Alternatives	Context / RAM	Downloads	Likes
Polyglot Ko 12.8B Instruct	2K / 25.9 GB	3187	3
Gollm 12.8B Instruct V2.3	2K / 25.9 GB	6	0
Gollm 12.8B Instruct V2.1	2K / 25.9 GB	8	0
Gollm 12.8B Instruct V2.0	2K / 25.9 GB	7	0
...lm 12.8B Instruct Tendency T45	2K / 25.9 GB	6	0
...t Ko 12.8B Chang Instruct Chat	2K / 25.9 GB	16	14

Note: green Score (e.g. "73.2") means that the model is better than etri-xainlp/polyglot-ko-12.8b-instruct.