Ask HN: Which model do you use for work?

The past little while has been filled with new LLM releases. I am curious to understand what you find to work best for your particular workflows and tasks.

8 points•george_max•5 days ago•15 comments•

#past #little #llm #curious #understand #workflows #filled #particular

The past little while has been filled with new LLM releases. I am curious to understand what you find to work best for your particular workflows and tasks.

15 comments

babamogambo883 days ago

https://github.com/STRAW-HAT-DEV/monkeyDcode.git

I use this coding agent with qwen 2.5b and sometimes other models from open router.. as a one piece fan lol this looks nice with all the anime stuff .. but the work it does is also promising .. I don't know if it has any issues or something .. but I feel great using it .. it almost does all the tasks I ask it to do ..

praash5 days ago

Qwen 3.8 27b-mlx running locally on Apple M4 48 GB. I only use local LLMs, mostly for getting technical suggestions and code snippet samples. Qwen 3.8 has been the first local model I've tried that has consistently given usable and impressive results.

laoxingAI4 days ago

GLM 5 is the main model I'm currently using. My usage with it is around 90,000 requests per month. Although its capability isn't the strongest, I think that because the quota is so large, it feels really great to use. For certain cases, I'll use the DeepSeek V4 model.

Actually, my latest open-source project, vocnly, was developed on GLM 5. It's a local voice-input tool, and it can be seen as an open-source alternative to Typeless. I think it works without any issues.

For certain cases, I'll use the DeepSeek V4 flash model.

KlyX4 days ago

I mostly use Claude - model depends and goes from Sonnet up to Fable (mostly Opus right now, Sonnet for easier task and Fable only seldom for very specific). Workplace-related we use ChatGPT 5.4/5 with LibreChat as Chatlayer. Would love to use Mistral more (as EU alternative), but my last test (though quite a while ago) I was a bit disappointed. May look into it again soon.

LUmBULtERA5 days ago

Astra on Extra High. Knowledge work, the right answer is much more important than a fast or cheap answer. If I were to switch to Anthropic, Opus 5.5 or Fable 5.1 on high or better.

moomoo114 days ago

same

Read the full thread on Hacker News →

15 comments

Related stories