steven0226/qwen3vl-8b-chartqa-gguf
Quantization (fewer layers) vs steven0226/qwen3vl-8b-chartqa-merged-16bit. steven0226/qwen3vl-8b-chartqa-gguf matches part of steven0226/qwen3vl-8b-chartqa-merged-16bit (399 of its 750 tensors; the rest of steven0226/qwen3vl-8b-chartqa-merged-16bit has no counterpart). On the shared part: steven0226/qwen3vl-8b-chartqa-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