# Multi-Precision Quantization

DeepSeek-R1-Llama-8B-F32-GGUF is the quantized version of DeepSeek-R1-Distill-Llama-8B, trained directly with reinforcement learning, featuring capabilities such as self-verification, reflection, and generating extended chain-of-thought reasoning.

This is a quantized version of Microsoft's Phi-4-reasoning model, optimized using llama.cpp for inference tasks and supporting multiple quantization options.

Gemma-3-12b model based on Google QAT (Quantization-Aware Training) weight quantization, offering multiple quantized versions to accommodate different hardware requirements.

FLUX.1-Redux-dev is a text-to-image generation model based on the FLUX technology stack, supporting the English language and adopting a non-commercial license.

This project provides the BGE embedding model stored in GGUF format, which is suitable for use with llama.cpp and offers better performance than transformers.