FadedRedStar/QwenPaw-Flash-9B-heretic-imatrix-GGUF

Same weights, converted (fewer layers) vs coder3101/QwenPaw-Flash-9B-heretic. FadedRedStar/QwenPaw-Flash-9B-heretic-imatrix-GGUF matches part of coder3101/QwenPaw-Flash-9B-heretic (3 of its 760 tensors; the rest of coder3101/QwenPaw-Flash-9B-heretic has no counterpart). On the shared part: Same weights stored in another dtype (F32 → BF16/F32).

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/1

On the Hub · Downloads on Model Pulse