DoppelReflEx
/

MoETest-3E2A-3x3B

Mixture of Experts

text-generation-inference

Model card Files Files and versions

A 3x3B Mixture of Expert (MoE) experimental model with 2 experts per token. Special thank MoV.

PS: Decent model, fast speed. Maybe it's silly, but fun enough if you use for message chat roleplay.

Downloads last month: -

Safetensors

Model size

8B params

Tensor type

BF16

·

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for DoppelReflEx/MoETest-3E2A-3x3B

NousResearch/Hermes-3-Llama-3.2-3B

SicariusSicariiStuff/Impish_LLAMA_3B

TroyDoesAI/BlackSheep-Llama3.2-3B

bunnycore/Llama-3.2-3B-Mix-Skill

Merge model

this model

Quantizations