{
 "name": "llm-speed signed LLM inference benchmarks (measured by llm-speed or community-submitted)",
 "version": "2026-11-06",
 "generated_at": "2026-11-06T01:13:09Z",
 "license": "CC BY 4.0",
 "license_url": "https://creativecommons.org/licenses/by/4.0/",
 "source": "https://llm-speed.com/data",
 "citation": "llm-speed. Signed LLM inference benchmarks (measured by llm-speed or community-submitted), version 2026-11-06. https://llm-speed.com/data. CC BY 4.0.",
 "fields": {
  "run_id": "Run ID; the run page is /r/<run_id>",
  "run_url": "Run page URL",
  "date": "Date the run was received (UTC, YYYY-MM-DD)",
  "hardware": "GPU (with its memory) or Apple Silicon as reported by the benchmark CLI; host CPU and RAM only for runs that kept work on the CPU (offload)",
  "model": "Model name as reported by the runtime",
  "model_size": "Parameter count as reported by the runtime, if any",
  "quant": "Quantization as reported by the runtime, if any",
  "runtime": "Inference runtime (backend), e.g. llama.cpp, ollama, mlx",
  "runtime_version": "Runtime version, if reported",
  "workload": "Suite workload, e.g. chat-short, agent-trace",
  "suite_version": "Benchmark suite version",
  "decode_tps": "Decode speed recorded by the signed run, tokens/second",
  "prefill_tps": "Prompt-processing speed recorded by the signed run, tokens/second",
  "ttft_ms": "Time to first token recorded by the signed run, ms",
  "prompt_tokens": "Prompt tokens",
  "output_tokens": "Generated tokens",
  "batch_size": "Concurrent sequences",
  "source": "'llm-speed' when llm-speed measured the run (listed in https://api.llm-speed.com/v1/run-sources), else 'community' (community-submitted, not measured by llm-speed)"
 },
 "run_count": 356,
 "row_count": 803,
 "source_counts": {
  "llm-speed": 419,
  "community": 384
 },
 "excluded_flagged_run_count": 1,
 "excluded_suspect_run_count": 1,
 "model_count": 116,
 "hardware_count": 19,
 "runtimes": [
  "llama.cpp",
  "mlx",
  "ollama"
 ],
 "files": {
  "csv": "/data/llm-speed-runs-2026-11-06.csv",
  "json": "/data/llm-speed-runs-2026-11-06.json"
 }
}
