# FP8 quantization

This model is the FP8 quantized version of Bielik-4.5B-v3.0-Instruct, utilizing AutoFP8 technology to quantize weights and activations into FP8 data type, reducing approximately 50% of disk space and GPU memory requirements.

This is an FP8 dynamic quantization version based on the Bielik-1.5B-v3.0-Instruct model, adapted for vLLM or SGLang inference frameworks. It uses AutoFP8 quantization technology to reduce parameter bytes from 16-bit to 8-bit, significantly lowering disk space and GPU VRAM requirements.

Qwen3-30B-A3B-FP8-dynamic is an FP8 quantized version of the Qwen3-30B-A3B model, significantly reducing memory requirements and computational costs while maintaining the high accuracy of the original model.

Qwen3-8B-FP8-dynamic is an optimized version of the Qwen3-8B model through FP8 quantization, significantly reducing GPU memory requirements and disk space usage while maintaining the original model's performance.

An efficient language model based on Qwen3-32B with FP8 dynamic quantization, significantly reducing memory requirements and improving computational efficiency

This is a 24B-parameter conditional generation model based on the Mistral3 architecture, optimized with FP8 dynamic quantization, suitable for multilingual text generation and visual understanding tasks.

QwQ-32B-FP8 is the FP8 quantized version of the QwQ-32B model, maintaining nearly the same accuracy as the BF16 version while supporting faster inference speed.

FP8 quantized version of QwQ-32B, reducing storage and memory requirements by 50% through dynamic quantization while maintaining 99.75% of the original model accuracy

FP8 quantized version of QwQ-32B, reducing storage and memory requirements by 50% through dynamic quantization while maintaining 99.75% of the original model accuracy

Flex.1-alpha-Fp8 is the safetensors format version of the Flex.1-alpha model with float8_e4m3fn weights, suitable for text-to-image generation tasks.

FP8 quantized version of Stable Diffusion 3.5 Large for text-to-image generation tasks.

FP8 quantized version of Llama-3.2-1B-Instruct, suitable for multilingual business and research applications, with performance close to the original model.

FP8 quantized version of Llama-3.2-3B-Instruct, suitable for multilingual commercial and research purposes, particularly ideal for assistant-like chat scenarios.

FP8 quantized version of Meta-Llama-3.1-70B, suitable for multilingual business and research applications, with both weights and activations quantized to FP8 format, reducing storage and memory requirements by approximately 50%.

FP8 quantized version of Meta-Llama-3.1-8B, suitable for multilingual business and research applications.

FP8 quantized version of Meta-Llama-3.1-70B-Instruct, suitable for multilingual commercial and research purposes, especially ideal for assistant-like chat scenarios.

FP8 quantized version of Meta-Llama-3.1-8B-Instruct, suitable for multilingual business and research applications, specially optimized for assistant-like chat scenarios.