TabbyAPI benchmarks
An inference engine for running open-weight LLMs locally.
3 community reports
TabbyAPI results by GPU
Hardware with reported TabbyAPI 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.
TabbyAPI on AMD RX 7900 XTX1 report
- Qwen3.8 125B · 6B active · 3.05bpw83.0 t/s(speculative, part in system RAM)
TabbyAPI on NVIDIA RTX 40901 report
- Qwen3.8 27B · 4.0bpw53.7 t/s, 885 t/s prompt
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 TabbyAPI
Every card is compared on one model, Qwen3.8 27B at 4-bit, the size and bit class that most cards here have plain runs of. A card with no run of that model shows none rather than a figure from a different model.
| GPU | VRAM | Reports | Median speed, Qwen3.8 27B 4-bit |
|---|---|---|---|
| AMD RX 7900 XTXamd | 24GB | 1 | no Qwen3.8 27B 4-bit run reported |
| NVIDIA RTX 3090nvidia | 24GB | 1 | no Qwen3.8 27B 4-bit run reported |
| NVIDIA RTX 4090nvidia | 24GB | 1 | Gen 53.7 t/sPP 885.0 t/s · n=1 |
TabbyAPI 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 TabbyAPI and on another engine, so llamaperf can't say how it compares on speed. Add a run.
Top models on TabbyAPI
Frequently asked
Is TabbyAPI faster than other engines?
llamaperf has no matched comparison for TabbyAPI yet: no card has plain runs of the same model size at the same bit class on TabbyAPI and on another engine. Speed claims about engines need that pairing, so this page doesn't make one.