Chopinab/SmolVLM2-2.2B-Instruct-Q5_K_M-GGUF
Quantization (fewer layers) vs HuggingFaceTB/SmolVLM2-2.2B-Instruct. Chopinab/SmolVLM2-2.2B-Instruct-Q5_K_M-GGUF matches part of HuggingFaceTB/SmolVLM2-2.2B-Instruct (219 of its 657 tensors; the rest of HuggingFaceTB/SmolVLM2-2.2B-Instruct has no counterpart). On the shared part: Chopinab/SmolVLM2-2.2B-Instruct-Q5_K_M-GGUF is a GGUF quantization (Q5_K_M) of the same weights: 49 tensors match exactly and 170 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/49, MLP 0/72, Attention 0/96, lm_head 0/1