naver-ellm/HyperCLOVAX-SEED-Vision-Instruct-3B-GGUF
Quantization (fewer layers) vs naver-hyperclovax/HyperCLOVAX-SEED-Vision-Instruct-3B. naver-ellm/HyperCLOVAX-SEED-Vision-Instruct-3B-GGUF matches part of naver-hyperclovax/HyperCLOVAX-SEED-Vision-Instruct-3B (290 of its 822 tensors; the rest of naver-hyperclovax/HyperCLOVAX-SEED-Vision-Instruct-3B has no counterpart). On the shared part: naver-ellm/HyperCLOVAX-SEED-Vision-Instruct-3B-GGUF is a GGUF quantization (Q4_K_M) of the same weights: 65 tensors match exactly and 225 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/65, MLP 0/96, Attention 0/128