Disya
/

Mistral-qwq-12b-merge-4bit

4-bit precision

Model card Files Files and versions

README.md exists but content is empty.

Downloads last month: 33

Safetensors

Model size

6.97B params

Tensor type

F32

·

F16

·

U8

·

Inference Providers NEW

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

Model tree for Disya/Mistral-qwq-12b-merge-4bit

Base model

Disya/Mistral-qwq-12b-merge

Quantized

(4)

this model

Finetunes