# Large model lightweighting

This is a quantized version of TheDrummer's Cydonia-24B-v3 model, quantized using llama.cpp, offering multiple quantization options to suit different hardware and usage scenarios.

This is a 4-bit quantized model of Qwen3-30B-A3B-abliterated, with a parameter scale equivalent to 8B, suitable for text generation tasks.

Quantized version based on Qwen/Qwen3-32B, using llama.cpp for quantization, supporting multiple quantization types for different hardware requirements.

GLM-4-32B-0414-4bit is an MLX format model converted from THUDM/GLM-4-32B-0414, supporting Chinese and English text generation tasks.

This is a GGUF format text generation model converted from the CoForAI/c4ai-command-r-08-2024 model, supporting multiple languages.

A Whisper Large V3 speech recognition model distilled and optimized with Malaysian datasets, supporting Malay and other languages