# Online weight optimization

A quantized version of the Microsoft NextCoder - 32B model, which uses the llama.cpp tool to quantize the original model for more efficient operation under different hardware conditions.

Multiple quantized versions of the Qwen3-14B-ft-limo model, generated using the imatrix option of llama.cpp, suitable for different performance and storage requirements

Qwen2.5-VL-32B-Instruct is a multimodal vision-language model with a parameter scale of 32B, supporting image understanding and text generation tasks.

The quantized version of Virtuoso-Lite, quantized using llama.cpp to improve the running efficiency on different hardware.