llama.cpp speed and memory options are hidden
llama.cpp tuning options such as speculative decoding and per-model KV cache quantization are not exposed in the app.
Tier II · Emerging Problems that are still building up.
3 public reports · first reported 16 April 2026 · last reported 3 May 2026
What's going wrong
Users of the Jan app running local models want more llama.cpp controls.
AI-assisted: written with the help of AI from the reports. The idea report has the full summary.
In the idea report
- The full summary.
- The products the 3 reports are about, and how many came each month.
- Related problems.
No business has been found with this problem yet, so the report has no contacts. All sales are final — no refunds. Pricing.