doldolggi/EvoCUA-8B-20260105-GGUF

Quantization (fewer layers) vs meituan/EvoCUA-8B-20260105. doldolggi/EvoCUA-8B-20260105-GGUF matches part of meituan/EvoCUA-8B-20260105 (399 of its 750 tensors; the rest of meituan/EvoCUA-8B-20260105 has no counterpart). On the shared part: doldolggi/EvoCUA-8B-20260105-GGUF is a GGUF quantization (Q8_0) of the same weights: 145 tensors match exactly and 254 within quantization error.

Tensors changed: Embeddings 0/1, Norms 0/145, MLP 0/108, Attention 0/144, lm_head 0/1

On the Hub · Downloads on Model Pulse