DevQuasar/sarvamai.sarvam-30b-GGUF
Quantization vs sarvamai/sarvam-30b. DevQuasar/sarvamai.sarvam-30b-GGUF is a GGUF quantization (Q2_K) of the same weights: 95 tensors match exactly and 78 within quantization error.
Tensors changed: Attention 0/19, Norms 0/77, MLP 0/75, Embeddings 0/1, lm_head 0/1