{
  "schema": "computearena-public-benchmark/1",
  "submission_id": "0d00cd50-feec-4314-9bf5-c7e54f50d030",
  "run_id": "29a1c71ef64a38a717ccb8bc0987fcb6",
  "created_at_unix_ms": 1789083516694,
  "submitted_by": "lukas",
  "model": {
    "canonical_id": "google/gemma-4-12B-it-qat-q4_0-unquantized",
    "identity_resolution": "artifact_verified",
    "identity_verification": "verified",
    "verified_at": "2026-09-11T12:18:35.929Z",
    "name": "Gemma-4 12B IT (smart Q4_0, QAT-lossless)",
    "architecture": "gemma4",
    "quantization": "Q4_0",
    "artifact": {
      "provider": "huggingface",
      "repo_id": "unsloth/gemma-4-12B-it-qat-GGUF",
      "revision": "980b060c40a8539ac159e0501a3e0f66a6365af3",
      "path": "gemma-4-12B-it-qat-UD-Q4_K_XL.gguf",
      "sha256": "90fd44e29e0d7cffeb0fd00dc73cfdab9ed0b0e95306ecf7821ea634c940c370"
    }
  },
  "runtime": {
    "name": "llama-cpp",
    "version": "b10901 (28ff09582)"
  },
  "benchmark": {
    "mode": "text",
    "chip": "Apple M5 Max",
    "backend": "MTL,BLAS",
    "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": 1254.073995168883
        },
        {
          "tokens": 256,
          "tokens_per_second": 1627.4439230481896
        },
        {
          "tokens": 512,
          "tokens_per_second": 1776.9611507423651
        },
        {
          "tokens": 1024,
          "tokens_per_second": 1693.0210526324481
        },
        {
          "tokens": 2048,
          "tokens_per_second": 1424.953862227504
        },
        {
          "tokens": 4096,
          "tokens_per_second": 1281.7509411370945
        },
        {
          "tokens": 8192,
          "tokens_per_second": 1140.4414220091937
        },
        {
          "tokens": 16384,
          "tokens_per_second": 982.392598233765
        }
      ],
      "decode": {
        "generated_tokens": 128,
        "tokens_per_second": 54.18178443755273
      }
    }
  }
}