mradermacher/Ling-flash-base-2.0-i1-GGUF
Quantization vs inclusionAI/Ling-flash-base-2.0. mradermacher/Ling-flash-base-2.0-i1-GGUF is a GGUF quantization (IQ3_S) of the same weights: 168 tensors match exactly and 135 within quantization error.
Tensors changed: Attention 0/33, Norms 0/136, MLP 0/131, Embeddings 0/1, lm_head 0/1, other 0/1