Ma7ee7 author hub

Qwen3 1.7B Depth Aggressive — Q4 K M GGUF A structured depth pruned and recovery trained variant of Qwen/Qwen3 1.7B https://huggingface.co/Qwen/Qwen3 1.7B , converted to GGUF and quantized as Q4 K M for llama.cpp compatible runtimes. Model changes Transformer layers: 28 → 24 Rem…