mradermacher/70B_Triage-GGUF

Quantization vs schonsense/70B_Triage. mradermacher/70B_Triage-GGUF is a GGUF quantization (Q8_0) of the same weights: 161 tensors match exactly and 562 within quantization error.

Tensors changed: Norms 0/161, MLP 0/240, Attention 0/320, lm_head 0/1, Embeddings 0/1

On the Hub · Downloads on Model Pulse