mradermacher/AfriqueGemma-12B-i1-GGUF

Quantization (fewer layers) vs McGill-NLP/AfriqueGemma-12B. mradermacher/AfriqueGemma-12B-i1-GGUF matches part of McGill-NLP/AfriqueGemma-12B (627 of its 1066 tensors; the rest of McGill-NLP/AfriqueGemma-12B has no counterpart). On the shared part: mradermacher/AfriqueGemma-12B-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 289 tensors match exactly and 338 within quantization error.

Tensors changed: Embeddings 0/1, Norms 0/289, MLP 0/144, Attention 0/192, lm_head 0/1

On the Hub · Downloads on Model Pulse