hugpadhugpad

speakleash / Bielik-1.5B-v3.0-Instruct-FP8-Dynamic

Text Generation1.6B6632Updated Jan 28, 2026
Hugging Face

Downloads

663

Likes

2

Last updated

Jan 28, 2026

License

apache-2.0

This model was obtained by quantizing the weights and activations of Bielik-1.5B-v3.0-Instruct to FP8 data type, ready for inference with vLLM = 0.5.0 or SGLang. AutoFP8 is used for quantization. This optimization reduces the number of bits per parameter from 16 to 8, reducing…

Tasks & library

  • text generation
  • transformers

Tags

  • transformers
  • llama
  • text-generation
  • finetuned
  • gguf
  • 8bit

Technical specifications

Parameters1.6B
Librarytransformers
Languagespl
Base modelspeakleash/Bielik-1.5B-v3.0-Instruct
Licenseapache-2.0