Open4bits/Nanbeige4.1-3B-GGUF

Quantization vs Nanbeige/Nanbeige4.1-3B. Open4bits/Nanbeige4.1-3B-GGUF is a GGUF quantization (Q8_0) of the same weights: 65 tensors match exactly and 226 within quantization error.

Tensors changed: lm_head 0/1, MLP 0/96, Attention 0/128, Norms 0/65, Embeddings 0/1

On the Hub · Downloads on Model Pulse