LiquidAI/LFM2.5-VL-1.6B-Extract-GGUF

Same weights, converted (fewer layers) vs LiquidAI/LFM2.5-VL-1.6B-Extract. LiquidAI/LFM2.5-VL-1.6B-Extract-GGUF matches part of LiquidAI/LFM2.5-VL-1.6B-Extract (138 of its 589 tensors; the rest of LiquidAI/LFM2.5-VL-1.6B-Extract 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