mradermacher/Fusion-7B-Quintessence-GGUF

Quantization vs ilevytate/Fusion-7B-Quintessence. mradermacher/Fusion-7B-Quintessence-GGUF is a GGUF quantization (Q8_0) of the same weights: 193 tensors match exactly and 674 within quantization error.

Tensors changed: MLP 0/288, Norms 0/193, Attention 0/384, Embeddings 0/1, lm_head 0/1

On the Hub · Downloads on Model Pulse