ssweens/Ling-2.6-flash-GGUF-YMMV
Quantization vs inclusionAI/Ling-2.6-flash. ssweens/Ling-2.6-flash-GGUF-YMMV is a GGUF quantization (Q8_0) of the same weights: 158 tensors match exactly and 135 within quantization error.
Tensors changed: MLP 0/131, Embeddings 0/1, Attention 0/33, Norms 0/126, lm_head 0/1, other 0/1