typhoon-ai/typhoon2.1-gemma3-12b-gguf
Quantization vs typhoon-ai/typhoon2.1-gemma3-12b. typhoon-ai/typhoon2.1-gemma3-12b-gguf is a GGUF quantization (Q4_K_M) of the same weights: 289 tensors match exactly and 337 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/289, MLP 0/144, Attention 0/192