{
  "schema": "computearena-public-benchmark/1",
  "submission_id": "e98de3e6-f9ed-4520-bdf0-5fc13b85fe07",
  "run_id": "15e0c69db9ae6e0f3e23d953fb2ea604",
  "created_at_unix_ms": 1789644703044,
  "submitted_by": "arki05",
  "model": {
    "canonical_id": "meta-llama/Llama-3.1-8B-Instruct",
    "identity_resolution": "artifact_verified",
    "identity_verification": "verified",
    "verified_at": "2026-09-18T05:23:14.872Z",
    "name": "Meta Llama 3.1 8B Instruct",
    "architecture": "llama",
    "quantization": "Q4_K_M",
    "artifact": {
      "provider": "huggingface",
      "repo_id": "bartowski/Meta-Llama-3.1-8B-Instruct-GGUF",
      "revision": "main",
      "path": "Meta-Llama-3.1-8B-Instruct-Q4_K_M.gguf",
      "sha256": "7b064f5842bf9532c91456deda288a1b672397a54fa729aa665952863033557c",
      "format": "gguf",
      "quantization_namespace": "gguf",
      "quantization_scheme": "Q4_K_M"
    }
  },
  "runtime": {
    "name": "llama-cpp",
    "version": "b1 (e64c0ea)"
  },
  "benchmark": {
    "mode": "text",
    "chip": "Tesla T10/Tesla T10/Tesla T10/Tesla T10",
    "backend": "CUDA",
    "protocol": {
      "report_schema": "computearena-benchmark/1",
      "benchmark_schema": "computearena-measurements/1",
      "telemetry_schema": "computearena-telemetry/1",
      "throughput_schema": "llama-bench-independent-pp-tg/1",
      "decode_initial_context_tokens": 0,
      "conditioning_schema": "computearena-conditioning/1",
      "conditioning_mode": "runtime_native_warmup",
      "cooldown_enabled": false
    },
    "parameters": {
      "decode_context_tokens": 0
    },
    "throughput": {
      "prefill": [
        {
          "tokens": 128,
          "tokens_per_second": 1623.5164848623183
        },
        {
          "tokens": 256,
          "tokens_per_second": 2909.3319150662005
        },
        {
          "tokens": 512,
          "tokens_per_second": 3390.2557071703595
        },
        {
          "tokens": 1024,
          "tokens_per_second": 3390.7283099453107
        },
        {
          "tokens": 2048,
          "tokens_per_second": 3374.130619145086
        },
        {
          "tokens": 4096,
          "tokens_per_second": 3313.5067386688424
        },
        {
          "tokens": 8192,
          "tokens_per_second": 3205.4415886150637
        },
        {
          "tokens": 16384,
          "tokens_per_second": 3002.2137711503597
        }
      ],
      "decode": {
        "generated_tokens": 128,
        "tokens_per_second": 136.1352575425008
      }
    }
  }
}