janhq/Jan-v2-VL-high-gguf
Quantization (fewer layers) vs janhq/Jan-v2-VL-high. janhq/Jan-v2-VL-high-gguf matches part of janhq/Jan-v2-VL-high (399 of its 750 tensors; the rest of janhq/Jan-v2-VL-high has no counterpart). On the shared part: janhq/Jan-v2-VL-high-gguf is a GGUF quantization (Q8_0) of the same weights: 145 tensors match exactly and 254 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, MLP 0/108, Norms 0/145, Attention 0/144