lmstudio-community/InternVL3_5-2B-GGUF
Quantization (fewer layers) vs OpenGVLab/InternVL3_5-2B. lmstudio-community/InternVL3_5-2B-GGUF matches part of OpenGVLab/InternVL3_5-2B (311 of its 657 tensors; the rest of OpenGVLab/InternVL3_5-2B has no counterpart). On the shared part: lmstudio-community/InternVL3_5-2B-GGUF is a GGUF quantization (Q8_0) of the same weights: 113 tensors match exactly and 198 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/113, MLP 0/84, Attention 0/112