pottokao/Qwen-Image-2.1-Text-Encoder-Heretic-DHQ-GGUF
Quantization (fewer layers) vs pottokao/Qwen-Image-2.1-Text-Encoder-Heretic. pottokao/Qwen-Image-2.1-Text-Encoder-Heretic-DHQ-GGUF matches part of pottokao/Qwen-Image-2.1-Text-Encoder-Heretic (399 of its 750 tensors; the rest of pottokao/Qwen-Image-2.1-Text-Encoder-Heretic has no counterpart). On the shared part: pottokao/Qwen-Image-2.1-Text-Encoder-Heretic-DHQ-GGUF is a GGUF quantization (Q4_K_M) of the same weights: 145 tensors match exactly and 254 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/145, MLP 0/108, Attention 0/144