Hugging Face's logo

deepsweet
/
YandexGPT-5-Lite-8B-Instruct-MLX-MXFP8

Text Generation
MLX
Safetensors
Russian
English
llama
conversational
8-bit precision
Model card Files
xet
 Community

This model was converted to MLX format from yandex/YandexGPT-5-Lite-8B-instruct using mlx-lm version 0.30.7:

mlx_lm.convert --hf-path yandex/YandexGPT-5-Lite-8B-instruct --mlx-path deepsweet/YandexGPT-5-Lite-8B-Instruct-MLX-MXFP8 --quantize --q-mode mxfp8 --q-group-size 32
Downloads last month
75
Safetensors
Model size
8B params
Tensor type
U8
·
U32
·
F16
·
MLX
Hardware compatibility
Log In to add your hardware

8-bit

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

Model tree for deepsweet/YandexGPT-5-Lite-8B-Instruct-MLX-MXFP8

Base model

yandex/YandexGPT-5-Lite-8B-pretrain
Finetuned
yandex/YandexGPT-5-Lite-8B-instruct
Quantized
(19)
this model

Collection including deepsweet/YandexGPT-5-Lite-8B-Instruct-MLX-MXFP8