{
  "schema": "computearena-public-benchmark/1",
  "submission_id": "ca427664-6feb-43bd-a9dc-1508755bbd8d",
  "run_id": "ca3fbbcdf468e924df63780bfa77c2b6",
  "created_at_unix_ms": 1789091891681,
  "submitted_by": "sarthak247",
  "model": {
    "canonical_id": "mistralai/Ministral-3-8B-Instruct-2512",
    "identity_resolution": "artifact_verified",
    "identity_verification": "verified",
    "verified_at": "2026-09-11T12:18:35.929Z",
    "name": "ministral-8B-Instruct-2512",
    "architecture": "mistral3",
    "quantization": "Q4_K_M",
    "artifact": {
      "provider": "huggingface",
      "repo_id": "mistralai/Ministral-3-8B-Instruct-2512-GGUF",
      "revision": "0102285ad796bd99af90f58de616092e5630e970",
      "path": "Ministral-3-8B-Instruct-2512-Q4_K_M.gguf",
      "sha256": "33e7a72cf5e6e2cfc2f2847075acc013d68bba023e35310cef86b5cf8fdca761"
    }
  },
  "runtime": {
    "name": "llama-cpp",
    "version": "b10902 (df03399b8)"
  },
  "benchmark": {
    "mode": "text",
    "chip": "NVIDIA GeForce RTX 4060 Laptop GPU",
    "backend": "CUDA",
    "protocol": {
      "report_schema": "computearena-benchmark/1",
      "benchmark_schema": "computearena-measurements/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": 1923.7857423128498
        },
        {
          "tokens": 256,
          "tokens_per_second": 2053.0049299178286
        },
        {
          "tokens": 512,
          "tokens_per_second": 2033.9374151299905
        },
        {
          "tokens": 1024,
          "tokens_per_second": 2033.6131443073225
        },
        {
          "tokens": 2048,
          "tokens_per_second": 1994.4074103949079
        },
        {
          "tokens": 4096,
          "tokens_per_second": 1912.1048521541031
        },
        {
          "tokens": 8192,
          "tokens_per_second": 1757.5237045622316
        },
        {
          "tokens": 16384,
          "tokens_per_second": 1486.085735419975
        }
      ],
      "decode": {
        "generated_tokens": 128,
        "tokens_per_second": 45.06968453448939
      }
    }
  }
}