mradermacher/SmolVLM2-2.2B-Instruct-GGUF

Same weights, converted (fewer layers) vs HuggingFaceTB/SmolVLM2-2.2B-Instruct. mradermacher/SmolVLM2-2.2B-Instruct-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: Same weights stored in another dtype (F32 → F16/F32).

Tensors changed: Embeddings 0/1, Norms 0/49, MLP 0/72, Attention 0/96, lm_head 0/1

On the Hub · Downloads on Model Pulse