What are the hardware requirements for EEVE Instruct Math 10.8B?

EEVE Instruct Math 10.8B requires approximately 21.6 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 EEVE Instruct Math 10.8B and how large is it?

EEVE Instruct Math 10.8B is developed by kuotient, 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 Instruct Math 10.8B?

EEVE Instruct Math 10.8B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

EEVE Instruct Math 10.8B by kuotient — VRAM 21.6GB, 4K context

Name: EEVE Instruct Math 10.8B
Author: kuotient

EEVE Instruct Math 10.8B is an open-source language model by kuotient. Features: 10.8b LLM, VRAM: 21.6GB, Context: 4K, License: cc-by-sa-4.0, Instruction-Based, Merged, LLM Explorer Score: 0.12.

Merged Model Arxiv:2306.01708 Arxiv:2311.03099 Arxiv:2402.14830 Base model:kuotient/eeve-math-... Base model:yanolja/yanoljanext... Conversational Endpoints compatible Instruct Ko Llama Model-index Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/kuotient/EEVE-Instruct-Math-10.8B

EEVE Instruct Math 10.8B Parameters and Internals

Model Type

text-generation

Additional Notes

This model serves as a proof of concept for combining distinct models to retain performance while extending usability.

Supported Languages

ko (native)

Input Output

Accepted Modalities:

text

LLM Name	EEVE Instruct Math 10.8B
Repository 🤗	https://huggingface.co/kuotient/EEVE-Instruct-Math-10.8B
Base Model(s)	yanolja/EEVE-Korean-Instruct-10.8B-v1.0 kuotient/EEVE-Math-10.8B-SFT yanolja/EEVE-Korean-Instruct-10.8B-v1.0 kuotient/EEVE-Math-10.8B-SFT
Merged Model	Yes
Model Size	10.8b
Required VRAM	21.6 GB
Updated	2026-08-06
Maintainer	kuotient
Model Type	llama
Instruction-Based	Yes
Model Files	9.9 GB: 1-of-3 9.8 GB: 2-of-3 1.9 GB: 3-of-3
Supported Languages	ko
Model Architecture	LlamaForCausalLM
License	cc-by-sa-4.0
Context Length	4096
Model Max Length	4096
Transformers Version	4.39.1
Tokenizer Class	LlamaTokenizer
Padding Token	</s>
Vocabulary Size	40960
Torch Data Type	bfloat16

Rank the EEVE Instruct Math 10.8B 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 Instruct Math 10.8B

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
Hkcode Meta QA5	4K / 21.6 GB	10	0
Eeve Leaderboard Inst V1.5	4K / 21.6 GB	2157	0
...struct 10.8B V1.0 Empathy V0.1	4K / 21.6 GB	7	0
EEVE Korean Instruct 10.8B Var	4K / 21.6 GB	5	4
EEVE 10.8 BOOK V0.1	4K / 21.6 GB	7	1
AlgograpV4	4K / 43.2 GB	8	0

Note: green Score (e.g. "73.2") means that the model is better than kuotient/EEVE-Instruct-Math-10.8B.