What are the hardware requirements for Llama 3 ELYZA Hermes 2x8B?

Llama 3 ELYZA Hermes 2x8B requires approximately 27.4 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 Llama 3 ELYZA Hermes 2x8B and how large is it?

Llama 3 ELYZA Hermes 2x8B is developed by keitokei1994, a model with 13.7b 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 Llama 3 ELYZA Hermes 2x8B?

Llama 3 ELYZA Hermes 2x8B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Llama 3 ELYZA Hermes 2x8B by keitokei1994 — VRAM 27.4GB, 8K context

Name: Llama 3 ELYZA Hermes 2x8B
Author: keitokei1994

Llama 3 ELYZA Hermes 2x8B is an open-source language model by keitokei1994. Features: 13.7b LLM, VRAM: 27.4GB, Context: 8K, License: llama3, MoE, LLM Explorer Score: 0.13.

Conversational En Endpoints compatible Ja Japanese Mixtral Moe Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/keitokei1994/Llama-3-ELYZA-hermes-2x8B

Llama 3 ELYZA Hermes 2x8B Parameters and Internals

Model Type

Mixture of Experts, Language Model

Additional Notes

Model was developed and tested using WSL2 and Google Colaboratory Pro, and verified using Llama.cpp and LMstudio.

Supported Languages

ja (Japanese), en (English)

LLM Name	Llama 3 ELYZA Hermes 2x8B
Repository 🤗	https://huggingface.co/keitokei1994/Llama-3-ELYZA-hermes-2x8B
Model Size	13.7b
Required VRAM	27.4 GB
Updated	2026-07-12
Maintainer	keitokei1994
Model Type	mixtral
Model Files	10.0 GB: 1-of-3 10.0 GB: 2-of-3 7.4 GB: 3-of-3
Supported Languages	ja en
Model Architecture	MixtralForCausalLM
License	llama3
Context Length	8192
Model Max Length	8192
Transformers Version	4.41.2
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<\|begin_of_text\|>
Vocabulary Size	128256
Torch Data Type	bfloat16

Rank the Llama 3 ELYZA Hermes 2x8B 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 Llama 3 ELYZA Hermes 2x8B

Best Alternatives	Context / RAM	Downloads	Likes
L3.1 MoE 2x8B V0.2	128K / 27.3 GB	9	9
... Deepseek DeepHermes E32 13.7B	128K / 54.9 GB	5	0
HAI SER	128K / 27.3 GB	7	16
L3.1 Celestial Stone 2x8B	128K / 27.3 GB	312	3
...ma 3 2x8B Instruct MoE 64K Ctx	64K / 27.3 GB	12	4
Penny Llama3 2x8b	8K / 27.3 GB	6	1
Kilo 2x8B	8K / 27.5 GB	12	1
Defne Llama3 2x8B	8K / 27.4 GB	15	6
Llama 3 Elyza Youko MoE 2x8B	8K / 27.3 GB	10	0
Inixion 2x8B V2	8K / 27.4 GB	6	2

Note: green Score (e.g. "73.2") means that the model is better than keitokei1994/Llama-3-ELYZA-hermes-2x8B.