khajaphysist
/

Qwen3-14B-FP8-Dynamic

Text Generation

text-generation-inference

compressed-tensors

Model card Files Files and versions

FP8 dynamic quatization for Ampere cards

Downloads last month: 2

Safetensors

Model size

15B params

Tensor type

BF16

·

F8_E4M3

·

Model tree for khajaphysist/Qwen3-14B-FP8-Dynamic

Base model

Qwen/Qwen3-14B-Base

Finetuned

Quantized

(159)

this model