mradermacher/calme-3.2-instruct-78b-GGUF

Quantization vs MaziyarPanahi/calme-3.2-instruct-78b. mradermacher/calme-3.2-instruct-78b-GGUF is a GGUF quantization (Q4_K_S) of the same weights: 431 tensors match exactly and 604 within quantization error.

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/173, MLP 0/258, Attention 0/602

On the Hub · Downloads on Model Pulse