isogen
/

Nanbeige4.1-3B-exl3-8bpw-h8

8-bit precision

Model card Files Files and versions

EXL3 quantization of Nanbeige4.1-3B, 8 bits per weight, including output layers.

Downloads last month: 8

Safetensors

Model size

2B params

Tensor type

F16

·

I16

·

Inference Providers NEW

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

Model tree for isogen/Nanbeige4.1-3B-exl3-8bpw-h8

Base model

Nanbeige/Nanbeige4-3B-Base

Finetuned

Nanbeige/Nanbeige4.1-3B

Quantized

(61)

this model