Sinensis
/

L3.3-Nevoria-R1-70b-AWQ

Text Generation

text-generation-inference

4-bit precision

Model card Files Files and versions

AWQ quantization of Steelskull/L3.3-Nevoria-R1-70b

quantization_config:
bits: 4
group_size: 128
quant_method: awq
version: gemm
zero_point: true

Downloads last month: 40

Safetensors

Model size

71B params

Tensor type

I32

·

BF16

·

Model tree for Sinensis/L3.3-Nevoria-R1-70b-AWQ

Base model

Steelskull/L3.3-Nevoria-R1-70b

Quantized

(20)

this model