mradermacher/granite-4.0-h-small-heretic_hi-GGUF

Quantization vs pszemraj/granite-4.0-h-small-heretic_hi. mradermacher/granite-4.0-h-small-heretic_hi-GGUF is a GGUF quantization (Q8_0) of the same weights: 121 tensors match exactly and 97 within quantization error.

Tensors changed: Embeddings 0/1, other 0/80, Norms 0/81, MLP 0/40, Attention 0/16

On the Hub · Downloads on Model Pulse