Why some small/medium models fail at grammar checking task?

Posted by Character-Blood3482@reddit | LocalLLaMA | View on Reddit | 4 comments

Recently, I try playing with gemma 4 (gemma-4-E4B-it-Q5_K_S.guff) and find out it fail at easy grammar check (it try to fix the already corrected word "contemporary"). I noticed the same mistake from openai/gpt-oss-20b and qwen3-next-80b-a3b-instruct.

Prompt:

grammar check: Although the Western Roman Empire collapsed in 476 CE, its sociopolitical and legal legacy continues to exert a profound influence on the institutional frameworks of the contemporary world.

Output:

The sentence has two spelling errors.

Here is the corrected version:

**Although** the Western Roman Empire collapsed in 476 CE, its sociopolitical and legal legacy continues to exert a profound influence on the institutional frameworks of the **contemporary** world.

***

### Corrections Made:

  1. **Although** $\rightarrow$ **Although** (Spelling correction)

  2. **contemporary** $\rightarrow$ **contemporary** (Spelling correction)