mradermacher/Light-IF-32B-GGUF

Quantization vs qihoo360/Light-IF-32B. mradermacher/Light-IF-32B-GGUF is a GGUF quantization (Q8_0) of the same weights: 257 tensors match exactly and 450 within quantization error.

Tensors changed: MLP 0/192, Attention 0/256, Norms 0/257, Embeddings 0/1, lm_head 0/1

On the Hub · Downloads on Model Pulse