KoboldCpp benchmarks
An inference engine for running open-weight LLMs locally.
2 community reports
KoboldCpp results by GPU
Hardware with reported KoboldCpp results, with each report's model, quant and speed, newest first. Runs on several cards, with speculative decoding, with batched requests or with part of the model in system RAM say so, since each describes a different setup.
KoboldCpp on NVIDIA RTX 30901 report
- DeepSeek V4 Flash 284B · 13B active · Q8KXL7.2 t/s, 111 t/s prompt(10 cards)
KoboldCpp on NVIDIA RTX 4060 Ti 16GB1 report
- Qwen3 30B · 3B active · Q4_K_M15.0 t/s(part in system RAM)
This engine doesn't yet have an editorial profile on llamaperf. The community reports below show how it's been used in practice across different hardware.
Compare GPUs running KoboldCpp
No plain run (one device, one request, no speculative decoding, the whole model in memory) with a generation speed has been reported on KoboldCpp yet, so there is no median to compare. The reports behind each card are listed below.
| GPU | VRAM | Reports |
|---|---|---|
| NVIDIA RTX 3090nvidia | 24GB | 1 |
| NVIDIA RTX 4060 Ti 16GBnvidia | 16GB | 1 |
KoboldCpp against other engines
Pairs of plain runs on the same card, of the same model size at the same bit class: one device, one request, no speculative decoding, the whole model in memory. Context length and build still differ between the two sides, and each side shows its own.
No matched pair yet. No card has plain runs of one model size at one bit class on KoboldCpp and on another engine, so llamaperf can't say how it compares on speed. Add a run.
Top models on KoboldCpp
Frequently asked
Is KoboldCpp faster than other engines?
llamaperf has no matched comparison for KoboldCpp yet: no card has plain runs of the same model size at the same bit class on KoboldCpp and on another engine. Speed claims about engines need that pairing, so this page doesn't make one.