mmnga/sarashina2.2-3b-instruct-v0.1-gguf
Quantization vs sbintuitions/sarashina2.2-3b-instruct-v0.1. mmnga/sarashina2.2-3b-instruct-v0.1-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, Embeddings 0/1, Norms 0/65, MLP 0/96, Attention 0/128