What are the hardware requirements for Gemma Ko 2B?

Gemma Ko 2B requires approximately 5.1 GB of VRAM and supports a context window of 8K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Gemma Ko 2B and how large is it?

Gemma Ko 2B is developed by beomi, a model with 2b 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 Gemma Ko 2B?

Gemma Ko 2B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Gemma Ko 2B by beomi — VRAM 5.1GB, 8K context

Name: Gemma Ko 2B
Author: beomi

Gemma Ko 2B is an open-source language model by beomi. Features: 2b LLM, VRAM: 5.1GB, Context: 8K, License: other, LLM Explorer Score: 0.12.

En Endpoints compatible Gemma Ko Pytorch Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/beomi/gemma-ko-2b

Gemma Ko 2B Parameters and Internals

Model Type

text generation

Additional Notes

These models can be used for various applications such as content creation, research, NLP techniques, etc. Known limitations include biases or gaps in training data, context and task complexity, language ambiguity, factual accuracy, and common sense.

Supported Languages

Korean (fluent), English (fluent)

Input Output

Input Format:

Text string, such as a question, a prompt, or a document to be summarized.

Output Format:

Generated Korean/English-language text in response to the input.

Performance Tips:

Longer context generally leads to better outputs, up to a certain point.

Release Notes

Version:

Date:

2024.03.26

Notes:

First release of Gemma-Ko 2B model

LLM Name	Gemma Ko 2B
Repository 🤗	https://huggingface.co/beomi/gemma-ko-2b
Model Size	2b
Required VRAM	5.1 GB
Updated	2026-05-29
Maintainer	beomi
Model Type	gemma
Model Files	5.0 GB: 1-of-2 0.1 GB: 2-of-2
Supported Languages	ko en
Model Architecture	GemmaForCausalLM
License	other
Context Length	8192
Model Max Length	8192
Transformers Version	4.38.2
Tokenizer Class	GemmaTokenizer
Padding Token	<pad>
Vocabulary Size	256000
Torch Data Type	bfloat16

Rank the Gemma Ko 2B 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 Gemma Ko 2B

Best Alternatives	Context / RAM	Downloads	Likes
Gemma 1.1 2B It	8K / 5.1 GB	209209	173
Gemma 2B It	8K / 5 GB	16802	3
Gemma 1.1 2B It	8K / 5 GB	43	3
Gemma 2B It Peru Legal Es V2	8K / 5.1 GB	8	1
Codegemma 2B	8K / 5.1 GB	33091	101
Bge Reranker V2 Gemma	8K / 10 GB	261121	87
Gita SastraGPT V1	8K / 5.1 GB	4	1
Caca Tinny 2B V3	8K / 5.1 GB	4	1
Pandas Tutor Gemma 2B	8K / 5.1 GB	6	1
Gemma Qlora Customer Support	8K / 5.1 GB	8	0

Note: green Score (e.g. "73.2") means that the model is better than beomi/gemma-ko-2b.