mradermacher/Geranium-105B-v1.0.0-i1-GGUF

Quantization vs tssst/Geranium-105B-v1.0.0. mradermacher/Geranium-105B-v1.0.0-i1-GGUF is a GGUF quantization (IQ3_S) of the same weights: 241 tensors match exactly and 842 within quantization error.

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/241, MLP 0/360, Attention 0/480

On the Hub · Downloads on Model Pulse