{
  "schema": "computearena-public-benchmark/1",
  "submission_id": "b85dc06a-f146-40b5-81cc-4f0a41d309db",
  "run_id": "c6c3400cfd9129a6be2ad9468ce5ce7d",
  "created_at_unix_ms": 1789110127825,
  "submitted_by": "arki05",
  "model": {
    "canonical_id": "Qwen/Qwen3-8B",
    "identity_resolution": "artifact_verified",
    "identity_verification": "verified",
    "verified_at": "2026-09-13T17:28:20.481Z",
    "name": "Qwen3-8B",
    "architecture": "qwen3",
    "quantization": "Q4_K_M",
    "artifact": {
      "provider": "huggingface",
      "repo_id": "unsloth/Qwen3-8B-GGUF",
      "revision": "a6adef130ffb23ddaf1a62fec9dced968c9bc482",
      "path": "Qwen3-8B-UD-Q4_K_XL.gguf",
      "sha256": "34a514d08f7449cb4a694a707aaa2eedccb7bb68290121bf5e5a569b2abe71c3"
    }
  },
  "runtime": {
    "name": "llama-cpp",
    "version": "b10809 (5266f24da)"
  },
  "benchmark": {
    "mode": "text",
    "chip": "Apple M5 Pro",
    "backend": "BLAS,MTL",
    "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": 1222.0226997354957
        },
        {
          "tokens": 256,
          "tokens_per_second": 1359.1239911487598
        },
        {
          "tokens": 512,
          "tokens_per_second": 1396.1173817222507
        },
        {
          "tokens": 1024,
          "tokens_per_second": 1362.8013702049718
        },
        {
          "tokens": 2048,
          "tokens_per_second": 1274.3328330665315
        },
        {
          "tokens": 4096,
          "tokens_per_second": 1127.2453458353166
        },
        {
          "tokens": 8192,
          "tokens_per_second": 909.6247676171398
        },
        {
          "tokens": 16384,
          "tokens_per_second": 637.107323597262
        }
      ],
      "decode": {
        "generated_tokens": 128,
        "tokens_per_second": 53.64171035376976
      }
    }
  }
}