mradermacher/QoQ-Med3-VL-8B-i1-GGUF
Quantization (fewer layers) vs ddvd233/QoQ-Med3-VL-8B. mradermacher/QoQ-Med3-VL-8B-i1-GGUF matches part of ddvd233/QoQ-Med3-VL-8B (399 of its 750 tensors; the rest of ddvd233/QoQ-Med3-VL-8B has no counterpart). On the shared part: mradermacher/QoQ-Med3-VL-8B-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 145 tensors match exactly and 254 within quantization error.
Tensors changed: Norms 0/145, MLP 0/108, Attention 0/144, Embeddings 0/1, lm_head 0/1