What are the hardware requirements for Etri Ones Solar?

Etri Ones Solar requires approximately 42.9 GB of VRAM and supports a context window of 4K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Etri Ones Solar and how large is it?

Etri Ones Solar is developed by leejaymin. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Etri Ones Solar perform on standard benchmarks?

Etri Ones Solar has the following published scores: MMLU 63.71. Compare against reference models on this page or on the LLM Explorer leaderboards.

Etri Ones Solar by leejaymin — VRAM 42.9GB, 4K context

Name: Etri Ones Solar
Author: leejaymin

Etri Ones Solar is an open-source language model by leejaymin. Features: LLM, VRAM: 42.9GB, Context: 4K, License: mit, Instruction-Based, LLM Explorer Score: 0.14, Arc: 62.6, HellaSwag: 84.3, MMLU: 63.7.

Dataset:instruction Endpoints compatible Instruct Ko Llama Pytorch Region:us Sharded

Model Card on HF 🤗: https://huggingface.co/leejaymin/etri-ones-solar

Etri Ones Solar Parameters and Internals

Model Type

auto-regressive, text generation

Supported Languages

ko (high)

Training Details

Model Architecture:

auto-regressive language model based on the solar transformer architecture

LLM Name	Etri Ones Solar
Repository 🤗	https://huggingface.co/leejaymin/etri-ones-solar
Required VRAM	42.9 GB
Updated	2026-08-06
Maintainer	leejaymin
Model Type	llama
Instruction-Based	Yes
Model Files	9.9 GB: 1-of-5 10.0 GB: 2-of-5 9.8 GB: 3-of-5 9.8 GB: 4-of-5 3.4 GB: 5-of-5
Supported Languages	ko
Model Architecture	LlamaForCausalLM
License	mit
Context Length	4096
Model Max Length	4096
Transformers Version	4.34.1
Tokenizer Class	LlamaTokenizer
Padding Token	<unk>
Vocabulary Size	32000
Torch Data Type	float32

Rank the Etri Ones Solar 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 Etri Ones Solar

Best Alternatives	Context / RAM	Downloads	Likes
Reverse Instruct	32K / 27 GB	8	3
Phi 3 Orpo V8.16	4K / 7.6 GB	7	0
Tinyllama Python	4K / 2.2 GB	13	2
Small Instruct	4K / 2.9 GB	10	1
Taiwan LLaMa V1.0	4K / 26 GB	35	78
Taiwan LLaMa V0.0	4K / 26 GB	14	1
Taiwan LLaMa V0.9	4K / 26 GB	13	0
Llama2 Ja Small Instruct	2K / 1.7 GB	5	1
Kolong Llama V0.1	2K / 13.7 GB	7	0
...ama Miniguanaco Instruct 121v2	2K / 2.2 GB	11	0