mmnga-o/llm-jp-4-33b-thinking-gguf

Quantization vs llm-jp/llm-jp-4-33b-thinking. mmnga-o/llm-jp-4-33b-thinking-gguf is a GGUF quantization (Q8_0) of the same weights: 129 tensors match exactly and 450 within quantization error.

Tensors changed: Embeddings 0/1, Norms 0/129, MLP 0/192, Attention 0/256, lm_head 0/1

On the Hub · Downloads on Model Pulse