DevQuasar/PowerInfer.SmallThinker-3B-Preview-GGUF
Same weights, converted vs Tiiny/SmallThinker-3B-Preview. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/73, MLP 0/108, Attention 0/252, lm_head 0/1
Same weights, converted vs Tiiny/SmallThinker-3B-Preview. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/73, MLP 0/108, Attention 0/252, lm_head 0/1