alt Hacker News> that local models are good enough for whatever they're peddling
they are not. Unless you are satisfied with plausible, but mostly garbage output.
Replies
throw1234567891 • today at 2:34 PM
I get results comparable to the saas. Maybe Anthropic sold you too much crack tokens.
➕ show 1 reply
fluoridation • today at 2:02 PM
Honestly, that's the output I get from non-local models, anyway. If I'm going to get plausible nonsense either way, I may as well run it on my own hardware.
chadgpt3 • today at 3:04 PM
isn't that literally all output an LLM generates?
They are actually quite a bit better than you might think. Qwen3.6 27B is pretty capable at coding.
For non-coding work, they are more than good enough. A lot of the ways my non-technical family members have interacted with AI would be perfectly served by using a local model.
After all, people were more than satisfied with the results from GPT 3. That has long since been surpassed by open weight models.