{
 "name": "llm-speed measured LLM inference benchmarks",
 "version": "2026-10-17.3",
 "generated_at": "2026-10-17T10:04:08Z",
 "license": "CC BY 4.0",
 "license_url": "https://creativecommons.org/licenses/by/4.0/",
 "source": "https://llm-speed.com/data",
 "citation": "llm-speed. Measured LLM inference benchmarks, version 2026-10-17.3. 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": "Hardware summary as reported by the benchmark CLI (accelerator + CPU + RAM)",
  "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": "Measured decode speed, tokens/second",
  "prefill_tps": "Measured prompt-processing speed, tokens/second",
  "ttft_ms": "Measured time to first token, ms",
  "prompt_tokens": "Prompt tokens",
  "output_tokens": "Generated tokens",
  "batch_size": "Concurrent sequences",
  "label": "Always 'measured': every row is a signed measurement"
 },
 "run_count": 277,
 "row_count": 522,
 "excluded_flagged_runs": [
  "r_pqjsvd-cub4"
 ],
 "model_count": 71,
 "hardware_count": 28,
 "runtimes": [
  "llama.cpp",
  "mlx",
  "ollama"
 ],
 "files": {
  "csv": "/data/llm-speed-runs-2026-10-17.3.csv",
  "json": "/data/llm-speed-runs-2026-10-17.3.json"
 }
}