Benchmarks
Accepted measurements
Every row below is one accepted standard-ai-v0.1 run: prompt-processing and generation throughput at a fixed context depth, measured with llama.cpp's own llama-bench. Exact values are shown here, not just charted — see /data for the full raw evidence behind each one.
| Hardware | Model | Context | Backend | Prompt processing | Generation | Status |
|---|---|---|---|---|---|---|
| Apple M1 Pro | llama 8B Q4_0 | 8192 | BLAS,MTL | 190.39 | 27.92 | PASS |
| Apple M1 Pro | qwen3 14B Q4_K - Medium | 8192 | BLAS,MTL | 97.09 | 11.73 | PASS |
| AMD Radeon(TM) Graphics | llama 8B Q4_0 | 8192 | Vulkan | 2511.81 | 102.31 | PASS |
| AMD Radeon(TM) Graphics | qwen3 14B Q4_K - Medium | 8192 | Vulkan | 1177.22 | 56.38 | PASS |
Units: tokens/second (tok/s), mean of 5 repetitions. Individual repetitions, standard deviation, and full raw llama-bench output are available per run on /data.