What are the hardware requirements for EcomGen 0.0.2v?

EcomGen 0.0.2v requires approximately 8.4 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 EcomGen 0.0.2v and how large is it?

EcomGen 0.0.2v is developed by UICHEOL-HWANG, a model with 2.1b 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 EcomGen 0.0.2v?

EcomGen 0.0.2v is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

EcomGen 0.0.2v by UICHEOL-HWANG — VRAM 8.4GB, 8K context

Name: EcomGen 0.0.2v
Author: UICHEOL-HWANG

EcomGen 0.0.2v is an open-source language model by UICHEOL-HWANG. Features: 2.1b LLM, VRAM: 8.4GB, Context: 8K, Instruction-Based, Merged, LLM Explorer Score: 0.17.

Merged Model Base model:finetune:kakaocorp/... Base model:kakaocorp/kanana-na... Conversational Endpoints compatible Instruct Ko Llama Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/UICHEOL-HWANG/EcomGen-0.0.2v

EcomGen 0.0.2v Parameters and Internals

LLM Name	EcomGen 0.0.2v
Repository 🤗	https://huggingface.co/UICHEOL-HWANG/EcomGen-0.0.2v
Base Model(s)	kakaocorp/kanana-nano-2.1b-instruct kakaocorp/kanana-nano-2.1b-instruct
Merged Model	Yes
Model Size	2.1b
Required VRAM	8.4 GB
Updated	2026-08-05
Maintainer	UICHEOL-HWANG
Model Type	llama
Instruction-Based	Yes
Model Files	5.0 GB: 1-of-2 3.4 GB: 2-of-2
Supported Languages	ko
Model Architecture	LlamaForCausalLM
Context Length	8192
Model Max Length	8192
Transformers Version	4.49.0
Tokenizer Class	PreTrainedTokenizer
Padding Token	<\|end_of_text\|>
Vocabulary Size	128256
Torch Data Type	float32

Rank the EcomGen 0.0.2v 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 EcomGen 0.0.2v

Best Alternatives	Context / RAM	Downloads	Likes
Kanana 1.5 2.1B Instruct 2505	32K / 4.6 GB	5371	37
Fc Reasoning 2.1B	32K / 4.2 GB	8	0
Kanana Nano 2.1B Instruct	8K / 4.2 GB	1025	75
Phi 3.5 Pii Test 13	128K / 7.6 GB	5	0
...Nano 2.1B Instruct Abliterated	8K / 8.4 GB	10	4

Note: green Score (e.g. "73.2") means that the model is better than UICHEOL-HWANG/EcomGen-0.0.2v.