chenly124/Qwen3-VL-8B-Thinking-heretic-Q4_K_M-GGUF

Quantization (fewer layers) vs coder3101/Qwen3-VL-8B-Thinking-heretic. chenly124/Qwen3-VL-8B-Thinking-heretic-Q4_K_M-GGUF matches part of coder3101/Qwen3-VL-8B-Thinking-heretic (399 of its 750 tensors; the rest of coder3101/Qwen3-VL-8B-Thinking-heretic has no counterpart). On the shared part: chenly124/Qwen3-VL-8B-Thinking-heretic-Q4_K_M-GGUF is a GGUF quantization (Q4_K_M) of the same weights: 145 tensors match exactly and 254 within quantization error.

Tensors changed: Embeddings 0/1, Norms 0/145, MLP 0/108, Attention 0/144, lm_head 0/1

On the Hub · Downloads on Model Pulse