DevQuasar/arcee-ai.Trinity-Large-Preview-GGUF
Quantization vs arcee-ai/Trinity-Large-Preview. DevQuasar/arcee-ai.Trinity-Large-Preview-GGUF is a GGUF quantization (Q8_0) of the same weights: 415 tensors match exactly and 482 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/361, MLP 0/234, Attention 0/300