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

Polyglot Ko 12.8B Inst requires approximately 51.4 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 Inst and how large is it?

Polyglot Ko 12.8B Inst is developed by nayohan, 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 Inst?

Polyglot Ko 12.8B Inst 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 Inst by nayohan — VRAM 51.4GB, 2K context

Name: Polyglot Ko 12.8B Inst
Author: nayohan

Polyglot Ko 12.8B Inst is an open-source language model by nayohan. Features: 12.8b LLM, VRAM: 51.4GB, Context: 2K, License: apache-2.0, LLM Explorer Score: 0.09.

Base model:eleutherai/polyglot... Base model:finetune:eleutherai... Dataset:dilab-hyu/koquality Deploy:azure Endpoints compatible Gpt-neox Gpt neox Ko Koquality Polyglot-ko Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/nayohan/polyglot-ko-12.8b-Inst

Polyglot Ko 12.8B Inst Parameters and Internals

Model Type

text generation

Supported Languages

ko (high)

Training Details

Data Sources:

DILAB-HYU/KoQuality, Kullm, OIG, KoAlpaca

Methodology:

instruct-tuning using 10% of the Instruction dataset

Hardware Used:

A100 40G GPU, CPU with 512GB

Model Architecture:

poylglot-ko

LLM Name	Polyglot Ko 12.8B Inst
Repository 🤗	https://huggingface.co/nayohan/polyglot-ko-12.8b-Inst
Base Model(s)	EleutherAI/polyglot-ko-12.8b EleutherAI/polyglot-ko-12.8b
Model Size	12.8b
Required VRAM	51.4 GB
Updated	2026-07-16
Maintainer	nayohan
Model Type	gpt_neox
Model Files	4.8 GB: 1-of-11 4.9 GB: 2-of-11 4.7 GB: 3-of-11 4.6 GB: 4-of-11 4.6 GB: 5-of-11 4.9 GB: 6-of-11 4.7 GB: 7-of-11 4.6 GB: 8-of-11 4.6 GB: 9-of-11 4.9 GB: 10-of-11 4.1 GB: 11-of-11
Supported Languages	ko
Model Architecture	GPTNeoXForCausalLM
License	apache-2.0
Context Length	2048
Model Max Length	2048
Transformers Version	4.35.0
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<\|endoftext\|>
Vocabulary Size	30003
Torch Data Type	float32

Rank the Polyglot Ko 12.8B Inst 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 Inst

Best Alternatives	Context / RAM	Downloads	Likes
...therAI Polyglot Ko 12.8B 4bits	2K / 7.7 GB	3	1
...pen Platypus Polyglot Ko 12.8B	2K / 51.4 GB	7	0
Polyglot Ko 12.8B Instruct	2K / 25.9 GB	3187	3
KoRnDAlpaca RAG Polyglot 12.8B	2K / 51.4 GB	6	0
KoRnDAlpaca RAG Polyglot 12.8B	2K / 51.4 GB	5	0
Kullm Polyglot 12.8B V3	2K / 25.9 GB	8	5
Polyglot Ko 12.8B Inst All	2K / 51.4 GB	1	1
Koquality Polyglot 12.8B	2K / 51.4 GB	12	0
Gollm 12.8B Instruct V2.3	2K / 25.9 GB	6	0
Gollm 12.8B Instruct V2.1	2K / 25.9 GB	8	0

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