tatsuyaaaaaaa
/

Qwen3-8B-FP8

compressed-tensors

Model card Files Files and versions

Qwen3-8Bをllm-compressorでFP8量子化したモデルです。

Downloads last month: 17

Safetensors

Model size

8B params

Tensor type

BF16

·

F8_E4M3

·

Inference Providers NEW

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

Model tree for tatsuyaaaaaaa/Qwen3-8B-FP8

Base model

Qwen/Qwen3-8B-Base

Finetuned

Quantized

(260)

this model

Dataset used to train tatsuyaaaaaaa/Qwen3-8B-FP8