Avg Speed44.59 t/s
Latency0.87 s
Total Tests5
Models1
Updated4/11/2026
Created At3/15/2026
A
429496 AI
A self-hosted AI API endpoint powered by llama.cpp, providing access to open-source LLMs.
A self-hosted AI API endpoint powered by llama.cpp, providing access to open-source LLMs.
| Model | Speed | Latency | Tests |
|---|---|---|---|
| Qwen3.5-35B-A3B-Q4_K_M.gguf | 44.59 t/s | 0.87s | 5 |
| Time | Model | Speed | Latency |
|---|---|---|---|
| Mar 15, 01:02 PM | Qwen3.5-35B-A3B-Q4_K_M.gguf | 44.59 t/s | 0.87s |