Products · Broad category
Local LLMs
Raised as a usability problem by 13 people on Hacker News over 4 years (2023–2026), in 13 threads.
This is a broad category rather than one product, so its issues aren't ranked on the home page.
No issue was raised by at least 3 people in 3 threads this year.
Every issue, all time, most people first
Local models run so slowly on laptops they are unusableUnreviewed
20232026- Running the model locally is too slow to be usable without huge hardware2026-02-05
- Local models run so slowly on the laptop they are unusable2025-05-22
- Local models respond too slowly to be practical for everyday tasks2025-04-20
Unreviewed issues were grouped by machine: Claude Haiku labelled each comment as a usability complaint, named what it's about and summed up the problem in a line, and a small model grouped similar problems. Nobody has checked them by hand. Expect mistakes.
The newest 11 complaints
- Can't tell what models can run on their hardware or how to use them2026-06-22
- Progress bar disappears when sidebar opened or app backgrounded, replaced by download button2026-03-25
- Local LLMs are too slow to use on ordinary hardware, needing tens of thousands in equipment2026-03-10
- Running the model locally is too slow to be usable without huge hardware2026-02-05
- Single or sub-single digit token throughput makes the model maddening and unusable2026-01-27
- Local models run so slowly on the laptop they are unusable2025-05-22
- Local models respond too slowly to be practical for everyday tasks2025-04-20
- Easy-to-use local model apps don't work well with Intel Arc GPU and run painfully slowly2024-06-04
- Clicking the feedback button does nothing, only shifts focus to browser chrome2024-02-28
- Voice assistant takes about 8 seconds to respond, slow to interact with2024-01-14
- Waits about 8 seconds after speaking before the first word is heard2024-01-13