mradermacher/Mistralv0.2-StarlingLM-FrankenMaid-10.5B-GGUF

Quantization vs ND911/Mistralv0.2-StarlingLM-FrankenMaid-10.5B. mradermacher/Mistralv0.2-StarlingLM-FrankenMaid-10.5B-GGUF is a GGUF quantization (Q8_0) of the same weights: 96 tensors match exactly and 330 within quantization error.

Tensors changed: MLP 0/141, Attention 0/188, Norms 0/95, lm_head 0/1, Embeddings 0/1

On the Hub · Downloads on Model Pulse