DevQuasar/swiss-ai.Apertus-70B-Instruct-2509-GGUF

Quantization vs swiss-ai/Apertus-70B-Instruct-2509. DevQuasar/swiss-ai.Apertus-70B-Instruct-2509-GGUF is a GGUF quantization (Q8_0) of the same weights: 321 tensors match exactly and 482 within quantization error.

Tensors changed: Embeddings 0/1, Norms 0/321, MLP 0/160, Attention 0/320, lm_head 0/1

On the Hub · Downloads on Model Pulse