KittyLM/kittylm-granite-4.2-3b-gguf

Quantization vs KittyLM/kittylm-granite-4.2-3b. KittyLM/kittylm-granite-4.2-3b-gguf is a GGUF quantization (Q8_0) of the same weights: 81 tensors match exactly and 282 within quantization error.

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/81, MLP 0/120, Attention 0/160

On the Hub · Downloads on Model Pulse