Ling-mini · 16B total / 3B active
The exact pinned IQ4_XS file completed true-CPU tests at three and four threads.
The exact pinned IQ4_XS file completed true-CPU tests at three and four threads.
The thread test shows a real speed and temperature tradeoff on the N5095 using one verified 8.8 GB artifact rather than a mutable model tag.
The rows on this page use IQ4_XS, pinned revision 8be84a0 through llama.cpp 9a286ac. They describe those exact artifacts and runs, not every version that shares the model name.
The fastest retained generation row is 4.083 tok/s through llama.cpp 9a286ac using CPU in 4 threads, 90 °C guard mode. The selected four-thread row improved generation 32.1% and completed under the disclosed 90 °C ceiling.
The rows below can come from different prompts and methods. Open the full test before treating two numbers as a direct comparison.
| Model and artifact | Runtime and mode | Generation | Prompt | Peak | State | Full test |
|---|---|---|---|---|---|---|
| Ling-mini-2.0 IQ4_XS, pinned revision 8be84a0 | llama.cpp 9a286ac CPU · 3 threads, 85 °C guard | 3.091 tok/s | 4.375 tok/s | 74 °C | Published result | Ling-mini thread test |
Open result detailsWhy this model is hereThe exact pinned IQ4_XS file completed true-CPU tests at three and four threads. The thread test shows a real speed and temperature tradeoff on the N5095 using one verified 8.8 GB artifact rather than a mutable model tag. What ranIQ4_XS, pinned revision 8be84a0 ran through llama.cpp 9a286ac using CPU in 3 threads, 85 °C guard mode on Youyeetoo X1S. The clean three-thread row stayed well below the normal thermal guard. Recorded setup
Artifact SHA-256 | ||||||
| Ling-mini-2.0 IQ4_XS, pinned revision 8be84a0 | llama.cpp 9a286ac CPU · 4 threads, 90 °C guard | 4.083 tok/s | 5.817 tok/s | 85 °C | Published result | Ling-mini thread test |
Open result detailsWhy this model is hereThe exact pinned IQ4_XS file completed true-CPU tests at three and four threads. The thread test shows a real speed and temperature tradeoff on the N5095 using one verified 8.8 GB artifact rather than a mutable model tag. What ranIQ4_XS, pinned revision 8be84a0 ran through llama.cpp 9a286ac using CPU in 4 threads, 90 °C guard mode on Youyeetoo X1S. The selected four-thread row improved generation 32.1% and completed under the disclosed 90 °C ceiling. Recorded setup
Artifact SHA-256 | ||||||
2026-08-31
The four-thread row used a disclosed 90 °C abort after the first attempt reached the normal 85 °C guard.
Open full test