avar6
/

Motif-3-Base-gguf

Model card Files Files and versions

Experimental ggufs of the final version of Motif-3. They require this llamacpp fork https://github.com/ggml-org/llama.cpp/pull/26298

Downloads last month: 79

GGUF

Model size

315B params

Architecture

motif3

Hardware compatibility

Log In to add your hardware

4-bit

Inference Providers NEW

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

Model tree for avar6/Motif-3-Base-gguf

Base model

Motif-Technologies/Motif-3-Base

Quantized

(1)

this model