What are the hardware requirements for Kyujin CoTy Platypus Ko 12.8B?

Kyujin CoTy Platypus Ko 12.8B requires approximately 25.9 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 Kyujin CoTy Platypus Ko 12.8B and how large is it?

Kyujin CoTy Platypus Ko 12.8B is developed by MarkrAI, 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 Kyujin CoTy Platypus Ko 12.8B?

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

Kyujin CoTy Platypus Ko 12.8B by MarkrAI — VRAM 25.9GB, 2K context

Name: Kyujin CoTy Platypus Ko 12.8B
Author: MarkrAI

Kyujin CoTy Platypus Ko 12.8B is an open-source language model by MarkrAI. Features: 12.8b LLM, VRAM: 25.9GB, Context: 2K, License: cc-by-nc-sa-4.0, LLM Explorer Score: 0.09.

Dataset:kyujinpy/kocot 2000 Endpoints compatible Gpt neox Ko Pytorch Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/MarkrAI/kyujin-CoTy-platypus-ko-12.8b

Kyujin CoTy Platypus Ko 12.8B Parameters and Internals

Model Type

text generation

Additional Notes

The license is `cc-by-nc-sa-4.0`.

Supported Languages

Korean (proficient)

Training Details

Data Sources:

KoCoT_2000 dataset

Methodology:

Fine-tuned using KO-Platypus2 and CoT-llama2 methodologies.

Hardware Used:

A100 GPU 40GB and COLAB

Model Architecture:

Auto-regressive language model based on the polyglot-ko transformer architecture.

Input Output

Input Format:

Models accept input text only.

Accepted Modalities:

text

Output Format:

Models generate text only.

LLM Name	Kyujin CoTy Platypus Ko 12.8B
Repository 🤗	https://huggingface.co/MarkrAI/kyujin-CoTy-platypus-ko-12.8b
Model Size	12.8b
Required VRAM	25.9 GB
Updated	2026-07-27
Maintainer	MarkrAI
Model Type	gpt_neox
Model Files	10.0 GB: 1-of-3 9.9 GB: 2-of-3 6.0 GB: 3-of-3 10.0 GB: 1-of-3 9.9 GB: 2-of-3 6.0 GB: 3-of-3
Supported Languages	ko
Model Architecture	GPTNeoXForCausalLM
License	cc-by-nc-sa-4.0
Context Length	2048
Model Max Length	2048
Transformers Version	4.34.0
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<\|endoftext\|>
Vocabulary Size	30080
Torch Data Type	float16

Rank the Kyujin CoTy Platypus Ko 12.8B 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 Kyujin CoTy Platypus Ko 12.8B

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
Polyglot Ko 12.8B Inst	2K / 51.4 GB	4	1

Note: green Score (e.g. "73.2") means that the model is better than MarkrAI/kyujin-CoTy-platypus-ko-12.8b.