Viewing profile — shironnnn_
shironnnn_
HN member- Joined
- Mon, Jun 15, 2026, 7:07 PM UTC
- HN karma
- 2
- Public activity
- 2 items
- HN profile
- View on Hacker News ↗
About shironnnn_
No profile information was provided.
Recent public activity
-
comment
Comment #48546693
if on MacOS I recommend llm-mlx which currently renders tokens 10%-15% faster than llama.cpp.
-
comment
Comment #48545709
I use SpecKit to create a very detailed plan with a high amount of specificity using paid Claude plan. Then I give it to local LLM (eg: Qwen / Gemma 4) via CLI. This is possible th…