mradermacher/S1-Base-1.5-32B-128K-GGUF

Quantization vs ScienceOne-AI/S1-Base-1.5-32B-128K. mradermacher/S1-Base-1.5-32B-128K-GGUF is a GGUF quantization (Q8_0) of the same weights: 257 tensors match exactly and 450 within quantization error.

Tensors changed: Norms 0/257, MLP 0/192, Attention 0/256, Embeddings 0/1, lm_head 0/1

On the Hub · Downloads on Model Pulse