# FP8 Quantization Optimization

Qwen3-14B-FP8-dynamic is an optimized large language model. By quantizing activation values and weights to the FP8 data type, it effectively reduces GPU memory requirements and improves computational throughput.

Llama-3.3-70B-Instruct-FP8-dynamic is an optimized large language model. By quantizing activations and weights to the FP8 data type, it reduces GPU memory requirements and improves computational throughput, supporting commercial and research use in multiple languages.

The NVIDIA Llama 3.1 405B Instruct FP8 model is a quantized version of Meta's Llama 3.1 405B Instruct model. It uses an optimized Transformer architecture and is an autoregressive language model. This model can be used for commercial or non-commercial purposes.