lmstudio-community/LFM2-VL-1.6B-GGUF
Quantization (fewer layers) vs LiquidAI/LFM2-VL-1.6B. lmstudio-community/LFM2-VL-1.6B-GGUF matches part of LiquidAI/LFM2-VL-1.6B (138 of its 575 tensors; the rest of LiquidAI/LFM2-VL-1.6B has no counterpart). On the shared part: lmstudio-community/LFM2-VL-1.6B-GGUF is a GGUF quantization (Q8_0) of the same weights: 45 tensors match exactly and 93 within quantization error.
Tensors changed: Embeddings 0/2, other 0/20, MLP 0/48, Norms 0/44, Attention 0/24