ikawrakow
/

Qwen3-30B-A3B

Model card Files Files and versions Community

ikawrakow commited on May 3

Commit

8d3bfbc

·

verified ·

1 Parent(s): da03cbf

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -3,8 +3,8 @@
 license: apache-2.0
 ---
-This repository contains 3 versions of Qwen3-30B-A3B quantized with `IQ4_KS`. The interesting part is that these models achieve a lower peplexity on
-`wiki.test.raw` than the original `bf16` model. This is interesting, considering that no QAT has been mentioned
 in the [Qwen3 announcement](https://qwenlm.github.io/blog/qwen3/). Hence I'm putting them out there for anyone interested in evaluating performance by means other than PPL,
 or just using for local inferrence.
 For more details see [this discussion](https://github.com/ikawrakow/ik_llama.cpp/discussions/359).

 license: apache-2.0
 ---
+This repository contains 3 versions of Qwen3-30B-A3B quantized with `IQ4_KS` (4.25 bpw quantization). The interesting part is that these models achieve a lower peplexity on
+`wiki.test.raw` than the original `bf16` model. This is surprising, considering that no QAT has been mentioned
 in the [Qwen3 announcement](https://qwenlm.github.io/blog/qwen3/). Hence I'm putting them out there for anyone interested in evaluating performance by means other than PPL,
 or just using for local inferrence.
 For more details see [this discussion](https://github.com/ikawrakow/ik_llama.cpp/discussions/359).