mradermacher/Austral-Reika-GGUF

Quantization vs NewEden-Forge/Austral-Reika. mradermacher/Austral-Reika-GGUF is a GGUF quantization (Q8_0) of the same weights: 89 tensors match exactly and 310 within quantization error.

Tensors changed: Embeddings 0/1, Norms 0/89, MLP 0/132, Attention 0/176, lm_head 0/1

On the Hub · Downloads on Model Pulse