What are the hardware requirements for EEVE Korean 10.8B V1.0 16K?

EEVE Korean 10.8B V1.0 16K requires approximately 21.6 GB of VRAM and supports a context window of 16K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed EEVE Korean 10.8B V1.0 16K and how large is it?

EEVE Korean 10.8B V1.0 16K is developed by maywell, a model with 10.8b 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 EEVE Korean 10.8B V1.0 16K?

EEVE Korean 10.8B V1.0 16K is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

EEVE Korean 10.8B V1.0 16K by maywell — VRAM 21.6GB, 16K context

Name: EEVE Korean 10.8B V1.0 16K
Author: maywell

EEVE Korean 10.8B V1.0 16K is an open-source language model by maywell. Features: 10.8b LLM, VRAM: 21.6GB, Context: 16K, License: apache-2.0, LLM Explorer Score: 0.12.

Arxiv:2402.14714 Base model:finetune:yanolja/ya... Base model:yanolja/yanoljanext... Conversational Endpoints compatible Llama Pytorch Region:us Sharded

Model Card on HF 🤗: https://huggingface.co/maywell/EEVE-Korean-10.8B-v1.0-16k

EEVE Korean 10.8B V1.0 16K Parameters and Internals

Model Type

Language Model

Use Cases

Areas:

Korean language tasks

Limitations:

Not fine-tuned with instruction-based training.

Considerations:

Further training advised for specific applications.

Supported Languages

Korean (Advanced)

Training Details

Data Sources:

Korean web-crawled datasets

Data Volume:

100GB Korean corpus

Methodology:

Subword-based embedding with a seven-stage training process involving parameter freezing and vocabulary expansion.

Model Architecture:

Vocabulary-extended version using subword embedding and parameter freezing.

LLM Name	EEVE Korean 10.8B V1.0 16K
Repository 🤗	https://huggingface.co/maywell/EEVE-Korean-10.8B-v1.0-16k
Base Model(s)	yanolja/EEVE-Korean-10.8B-v1.0 yanolja/EEVE-Korean-10.8B-v1.0
Model Size	10.8b
Required VRAM	21.6 GB
Updated	2026-06-06
Maintainer	maywell
Model Type	llama
Model Files	10.0 GB: 1-of-3 10.0 GB: 2-of-3 1.6 GB: 3-of-3
Model Architecture	LlamaForCausalLM
License	apache-2.0
Context Length	16384
Model Max Length	16384
Transformers Version	4.34.0
Tokenizer Class	LlamaTokenizer
Padding Token	</s>
Vocabulary Size	40960
Torch Data Type	float16

Rank the EEVE Korean 10.8B V1.0 16K 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 EEVE Korean 10.8B V1.0 16K

Best Alternatives	Context / RAM	Downloads	Likes
...Korean Instruct 10.8B V1.0 32K	32K / 21.6 GB	40	10
...EVE Korean Instruct 10.8B V1.0	4K / 21.6 GB	9491	160
...anoljaNEXT EEVE Instruct 10.8B	4K / 21.6 GB	14441	166
...Judgment Transducer 10.8B V2.0	4K / 21.6 GB	5	0
EEVE Korean Medical 10.8B	4K / 21.6 GB	7	0
Myungdonggil S5	4K / 43.2 GB	9	0
EEVE Korean 10.8B RAFT	4K / 43.2 GB	7	0
T3Q LLM TE NLI Lora16 32 V1.0	4K / 21.6 GB	4	1
T3Q LLM TE NLI Lora16 V1.0	4K / 21.6 GB	7	2
T3Q LLM TE NLI Dora4 V1.0	4K / 21.6 GB	7	0

Note: green Score (e.g. "73.2") means that the model is better than maywell/EEVE-Korean-10.8B-v1.0-16k.