What are the hardware requirements for Gemma Han 2B?

Gemma Han 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 Han 2B and how large is it?

Gemma Han 2B is developed by ping98k, 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 Han 2B?

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

Gemma Han 2B by ping98k — VRAM 5.1GB, 8K context

Name: Gemma Han 2B
Author: ping98k

Gemma Han 2B is an open-source language model by ping98k. Features: 2b LLM, VRAM: 5.1GB, Context: 8K, Quantized, Instruction-Based, LLM Explorer Score: 0.12.

Base model:quantized:unsloth/g... Base model:unsloth/gemma-2b Conversational Dataset:pythainlp/han-instruct... Endpoints compatible Gemma Gguf Instruct Quantized Region:us Safetensors Sharded Tensorflow Th

Model Card on HF 🤗: https://huggingface.co/ping98k/gemma-han-2b

Gemma Han 2B Parameters and Internals

Model Type

text generation

Use Cases

Primary Use Cases:

creating poetry on specified themes, coding examples, short story generation, advertisement creation

Limitations:

overfits to train data from han dataset and may not answer queries outside of it

Additional Notes

The model overfits the train data, limiting its ability to respond to queries not covered in the training dataset.

Supported Languages

languages_supported (Thai), proficiency_level ()

Training Details

Data Sources:

pythainlp/han-instruct-dataset-v2.0

Methodology:

finetuning

LLM Name	Gemma Han 2B
Repository 🤗	https://huggingface.co/ping98k/gemma-han-2b
Base Model(s)	Gemma 2B unsloth/gemma-2b
Model Size	2b
Required VRAM	5.1 GB
Updated	2026-07-21
Maintainer	ping98k
Model Type	gemma
Instruction-Based	Yes
Model Files	1.6 GB 5.0 GB: 1-of-2 0.1 GB: 2-of-2
Supported Languages	th
GGUF Quantization	Yes
Quantization Type	gguf
Model Architecture	GemmaForCausalLM
Context Length	8192
Model Max Length	8192
Transformers Version	4.39.3
Tokenizer Class	GemmaTokenizer
Padding Token	<pad>
Vocabulary Size	256000
Torch Data Type	bfloat16

Rank the Gemma Han 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 Han 2B

Best Alternatives	Context / RAM	Downloads	Likes
...os Code Instruct Finetune Test	8K / 5.1 GB	39	0
Gemma 2B Inst Aipi	8K / 5.1 GB	54	2
...ma Code Instruct Finetune Test	8K / 5.1 GB	45	0
Gemma 2B Instruct	8K / 5.1 GB	85	0
...Code 2B Instruct Finetune Test	8K / 5.1 GB	33	0
Gita SastraGPT V1	8K / 5.1 GB	4	1
Pandas Tutor Gemma 2B	8K / 5.1 GB	6	1
... 2B Finetuned Sft Navarasa 2.0	8K / 10 GB	536	27
...ma Code Instruct Finetune Test	8K / 5.1 GB	30	0
Gemma 2B Sft Preview	8K / 5 GB	13	0

Note: green Score (e.g. "73.2") means that the model is better than ping98k/gemma-han-2b.