What are the hardware requirements for Llama 3 8Bx2 MoE DPO?

Llama 3 8Bx2 MoE DPO 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 8Bx2 MoE DPO and how large is it?

Llama 3 8Bx2 MoE DPO is developed by cloudyu, 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 8Bx2 MoE DPO?

Llama 3 8Bx2 MoE DPO is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Llama 3 8Bx2 MoE DPO by cloudyu — VRAM 27.4GB, 8K context

Name: Llama 3 8Bx2 MoE DPO
Author: cloudyu

Llama 3 8Bx2 MoE DPO is an open-source language model by cloudyu. Features: 13.7b LLM, VRAM: 27.4GB, Context: 8K, License: apache-2.0, MoE, Instruction-Based, LLM Explorer Score: 0.12.

Conversational Endpoints compatible Instruct Mixtral Moe Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/cloudyu/Llama-3-8Bx2-MOE-DPO

Llama 3 8Bx2 MoE DPO Parameters and Internals

Model Type

text generation

Input Output

Accepted Modalities:

text

Output Format:

text

LLM Name	Llama 3 8Bx2 MoE DPO
Repository 🤗	https://huggingface.co/cloudyu/Llama-3-8Bx2-MOE-DPO
Model Size	13.7b
Required VRAM	27.4 GB
Updated	2026-08-02
Maintainer	cloudyu
Model Type	mixtral
Instruction-Based	Yes
Model Files	10.0 GB: 1-of-3 10.0 GB: 2-of-3 7.4 GB: 3-of-3
Model Architecture	MixtralForCausalLM
License	apache-2.0
Context Length	8192
Model Max Length	8192
Transformers Version	4.40.1
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<\|begin_of_text\|>
Vocabulary Size	128256
Torch Data Type	float16

Rank the Llama 3 8Bx2 MoE DPO 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 8Bx2 MoE DPO

Best Alternatives	Context / RAM	Downloads	Likes
L3.1 Celestial Stone 2x8B	128K / 27.3 GB	312	3
...ma 3 2x8B Instruct MoE 64K Ctx	64K / 27.3 GB	12	4
Defne Llama3 2x8B	8K / 27.4 GB	15	6
Inixion 2x8B V2	8K / 27.4 GB	6	2
MoE Llama3 8bx2 Rag	8K / 27.3 GB	7	0
Inixion 2x8B	8K / 27.5 GB	9	1
Llama 3 Chatty 2x8B	8K / 27.3 GB	6	11
FinalFintetuning XVIII 2x8B	8K / 27.5 GB	11	4
Llama 3 Teal Instruct 2x8B MoE	8K / 27.3 GB	8	0
...lama3 2x8b MoE 41K Experiment1	8K / 27.3 GB	5	2

Note: green Score (e.g. "73.2") means that the model is better than cloudyu/Llama-3-8Bx2-MOE-DPO.