mradermacher/lfm2-vl-textualis-GGUF

Same weights, converted (fewer layers) vs wjbmattingly/lfm2-vl-textualis. mradermacher/lfm2-vl-textualis-GGUF matches part of wjbmattingly/lfm2-vl-textualis (138 of its 351 tensors; the rest of wjbmattingly/lfm2-vl-textualis has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: Embeddings 0/2, other 0/20, MLP 0/48, Norms 0/44, Attention 0/24

On the Hub · Downloads on Model Pulse