metadata
license: apache-2.0
base_model:
- Qwen/Qwen2.5-14B
Qwen2.5-14B-All-Variants-q8_0-q6_K-GGUF
This repo contains GGUF quantizations of Qwen/Qwen2.5-14B, Qwen/Qwen2.5-14B-Instruct, and Qwen/Qwen2.5-Coder-14B-Instruct models at q6_K, using q8_0 for output and embedding tensors.