Update README.md

README.md

@@ -126,7 +126,7 @@ ggc la
 
 ### update
 - [clip-l-v2](https://huggingface.co/calcuis/pig-encoder/blob/main/clip_l_v2_fp32-f16.gguf): missing tensor `text_projection.weight` added
-- kontext-v2: except single and double blocks, all in `f32` status; advantage: 1) avoid key breaking issue, since some inference engines only dequant blocks; 2) compatible for non-cuda machines, as most of them cannot run `bf16` tensors
+- kontext-v2: except single and double blocks, all in `f32` status; pros: 1) avoid key breaking issue, since some inference engines only dequant blocks; 2) compatible for non-cuda machines, as most of them cannot run `bf16` tensors; cons: a little bit large in file size
 - kontext-v3: `i-quant` attempt (upgrade your node to the latest version for new quant support)
 - kontext-v4: `t-quant`; runnable recently; for speed test/experimental purposes