{
  "schema": "computearena-public-benchmark/1",
  "submission_id": "68526f54-114e-44f9-8b3a-765acba4fca8",
  "run_id": "e535dca1a864496ed1fcdf313140b23a",
  "created_at_unix_ms": 1789096514184,
  "submitted_by": "sarthak247",
  "model": {
    "canonical_id": "zai-org/GLM-4.6V-Flash",
    "identity_resolution": "artifact_verified",
    "identity_verification": "verified",
    "verified_at": "2026-09-11T12:18:35.929Z",
    "name": "Glm-4.6V-Flash",
    "architecture": "glm4",
    "quantization": "Q4_0",
    "artifact": {
      "provider": "huggingface",
      "repo_id": "unsloth/GLM-4.6V-Flash-GGUF",
      "revision": "c78a0727cb5ee489db2f218a212f613943023ee8",
      "path": "GLM-4.6V-Flash-Q4_0.gguf",
      "sha256": "c725c1f372976607849d41432606b1f4dcccf17aa0858510fb05f2a396692f84"
    }
  },
  "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": 1943.4947679386216
        },
        {
          "tokens": 256,
          "tokens_per_second": 2086.57626477664
        },
        {
          "tokens": 512,
          "tokens_per_second": 2078.9634714245094
        },
        {
          "tokens": 1024,
          "tokens_per_second": 2060.6278594415157
        },
        {
          "tokens": 2048,
          "tokens_per_second": 2012.7800322941748
        },
        {
          "tokens": 4096,
          "tokens_per_second": 1918.4479683436955
        },
        {
          "tokens": 8192,
          "tokens_per_second": 1741.9293355697248
        },
        {
          "tokens": 16384,
          "tokens_per_second": 1446.8900794869853
        }
      ],
      "decode": {
        "generated_tokens": 128,
        "tokens_per_second": 43.14593443617986
      }
    }
  }
}