Qwen3-Coder-Next benchmark on an M4 Pro · 64 GB

{
  "runId": "run_bc96c48f-5bdc-4f71-bd0e-1fa4f354c1ee",
  "bundleId": "llamacpp-qwen3-coder-next-q4_k_m.gguf-fc7334",
  "status": "verified",
  "promptTokens": 40960,
  "completionTokens": 10240,
  "contextLength": 5120,
  "harness": {
    "version": "0.1.18",
    "gitSha": "unknown"
  },
  "runtime": {
    "name": "llama.cpp",
    "version": "b8793",
    "buildFlags": "metal"
  },
  "model": {
    "displayName": "Qwen3-Coder-Next",
    "format": "gguf",
    "quant": "q4_k_m",
    "architecture": "qwen3next",
    "source": "unsloth/Qwen3-Coder-Next-GGUF:Qwen3-Coder-Next-Q4_K_M.gguf",
    "fileSizeBytes": 48528320544,
    "lab": {
      "name": "Qwen",
      "slug": "qwen"
    },
    "quantizedBy": {
      "name": "Unsloth",
      "slug": "unsloth"
    }
  },
  "device": {
    "cpu": "Apple M4 Pro",
    "cpuCores": 14,
    "gpu": "Apple M4 Pro",
    "gpuCores": 20,
    "gpuCount": 1,
    "ramGb": 64,
    "osName": "macOS",
    "osVersion": "26.3"
  },
  "decodeTpsMean": 39.4,
  "prefillTpsMean": 469.7,
  "ttftP50Ms": 8857.1,
  "idleTpsMean": 13998.5,
  "peakRssMb": 29431.9,
  "trialsPassed": 10,
  "trialsTotal": 10,
  "runnabilityScore": 0.5597806483677455,
  "bundleSha256": "e3431975c5a102e540b74be99bb0801235695686ec1801c2ded80ded18d71dfb",
  "createdAt": "2026-04-04T02:45:13.899Z"
}