What are the hardware requirements for EleutherAI Polyglot Ko 12.8B 4bits?

EleutherAI Polyglot Ko 12.8B 4bits requires approximately 7.7 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 EleutherAI Polyglot Ko 12.8B 4bits and how large is it?

EleutherAI Polyglot Ko 12.8B 4bits is developed by RichardErkhov, 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 EleutherAI Polyglot Ko 12.8B 4bits?

EleutherAI Polyglot Ko 12.8B 4bits is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

EleutherAI Polyglot Ko 12.8B 4bits by RichardErkhov — VRAM 7.7GB, 2K context

Name: EleutherAI Polyglot Ko 12.8B 4bits
Author: RichardErkhov

EleutherAI Polyglot Ko 12.8B 4bits is an open-source language model by RichardErkhov. Features: 12.8b LLM, VRAM: 7.7GB, Context: 2K, License: apache-2.0, LLM Explorer Score: 0.13.

Arxiv:2104.09864 Arxiv:2204.04541 Arxiv:2306.02254 4-bit Bitsandbytes Endpoints compatible Gpt neox Pytorch Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/RichardErkhov/EleutherAI_-_polyglot-ko-12.8b-4bits

EleutherAI Polyglot Ko 12.8B 4bits Benchmarks

LLME Score: 0.12907

^nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

What is the LLM Explorer Rank (Score)

EleutherAI Polyglot Ko 12.8B 4bits (RichardErkhov/EleutherAI_-_polyglot-ko-12.8b-4bits)

🌟 Advertise your project 🚀

EleutherAI Polyglot Ko 12.8B 4bits Parameters and Internals

Model Type

autoregressive, language model

Use Cases

Areas:

Research, Commercial Applications

Applications:

Text generation, Language comprehension, Model evaluation

Primary Use Cases:

Next token prediction in Korean

Limitations:

Model may not produce the most factual or accurate responses and can produce offensive content.

Considerations:

Use with appropriate filtering mechanisms for sensitive content.

Supported Languages

ko (Full)

Training Details

Data Sources:

Korean blog posts, Korean news dataset, Modu corpus, Korean patent dataset, Korean Q & A dataset, KcBert dataset, Korean fiction dataset, Korean online comments, Korean wikipedia, Clova call, Naver sentiment movie corpus, Korean hate speech dataset, Open subtitles, AIHub various tasks datasets, Standard Korean language dictionary

Data Volume:

863 GB (1.2TB before processing)

Methodology:

Trained for 167 billion tokens over 301,000 steps using GPT-NeoX framework with cross-entropy loss.

Context Length:

2048

Hardware Used:

256 A100 GPUs

Model Architecture:

40 transformer layers, model dimension 5120, feedforward dimension 20480, 40 heads of dimension 128, Rotary Position Embedding applied to 64 dimensions.

Responsible Ai Considerations

Fairness:

Polyglot-Ko may produce socially unacceptable or offensive content.

Transparency:

Open-source release with citation information provided.

Accountability:

Human curation recommended to filter sensitive content.

Mitigation Strategies:

Masking of personally identifiable information (PII) in the pre-processing stage.

Input Output

Input Format:

Text prompt in Korean

Accepted Modalities:

text

Output Format:

Text generation

Performance Tips:

Ensure suitable hardware for large model execution and sufficient memory capacity.

LLM Name	EleutherAI Polyglot Ko 12.8B 4bits
Repository 🤗	https://huggingface.co/RichardErkhov/EleutherAI_-_polyglot-ko-12.8b-4bits
Model Size	12.8b
Required VRAM	7.7 GB
Updated	2026-04-22
Maintainer	RichardErkhov
Model Type	gpt_neox
Model Files	5.0 GB: 1-of-2 2.7 GB: 2-of-2
Supported Languages	ko
Model Architecture	GPTNeoXForCausalLM
License	apache-2.0
Context Length	2048
Model Max Length	2048
Transformers Version	4.39.3
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<\|endoftext\|>
Vocabulary Size	30080
Torch Data Type	float16

Best Alternatives to EleutherAI Polyglot Ko 12.8B 4bits

Best Alternatives	Context / RAM	Downloads	Likes
...pen Platypus Polyglot Ko 12.8B	2K / 51.4 GB	5	0
Polyglot Ko 12.8B Instruct	2K / 25.9 GB	3187	3
KoRnDAlpaca RAG Polyglot 12.8B	2K / 51.4 GB	8	0
KoRnDAlpaca RAG Polyglot 12.8B	2K / 51.4 GB	5	0
Kullm Polyglot 12.8B V3	2K / 25.9 GB	6	5
Polyglot Ko 12.8B Inst All	2K / 51.4 GB	5	1
Polyglot Ko 12.8B	2K / 25.8 GB	3348	85
Koquality Polyglot 12.8B	2K / 51.4 GB	7	0
Gollm 12.8B Instruct V2.3	2K / 25.9 GB	14	0
Polyglot Ko 12.8B Inst	2K / 51.4 GB	4	1

Rank the EleutherAI Polyglot Ko 12.8B 4bits Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

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

What open-source LLMs or SLMs are you in search of? 53310 in total.

Email us: info@extractum.io. Our Privacy Policy | Terms and Conditions | Suggest an improvement.

Our Social Media →

Original data from HuggingFace, OpenCompass and various public git repos.

Check out Ag3ntum — our secure, self-hosted AI agent for server management.

Release v20260328a

Support LLM Explorer

EleutherAI Polyglot Ko 12.8B 4bits by RichardErkhov

» All LLMs » RichardErkhov » EleutherAI Polyglot Ko 12.8B 4bits URL Share it on

EleutherAI Polyglot Ko 12.8B 4bits Benchmarks

EleutherAI Polyglot Ko 12.8B 4bits Parameters and Internals

Best Alternatives to EleutherAI Polyglot Ko 12.8B 4bits

Rank the EleutherAI Polyglot Ko 12.8B 4bits Capabilities

What open-source LLMs or SLMs are you in search of? 53310 in total.