Qwen3-Coder-Next benchmark on an M1 Ultra · 64 GB

{
  "runId": "run_da84b8bb-a3de-4f9d-8e44-2217e7f31cf7",
  "bundleId": "mlx-qwen3-coder-next-4bit-62bcde",
  "status": "verified",
  "promptTokens": 40960,
  "completionTokens": 10240,
  "contextLength": 5120,
  "harness": {
    "version": "0.1.21",
    "gitSha": "unknown"
  },
  "runtime": {
    "name": "mlx_lm",
    "version": "0.31.2",
    "buildFlags": null
  },
  "model": {
    "displayName": "Qwen3-Coder-Next",
    "format": "mlx",
    "quant": "4bit",
    "architecture": "qwen3_next",
    "source": "mlx-community/Qwen3-Coder-Next-4bit",
    "fileSizeBytes": 44844286500,
    "lab": {
      "name": "Qwen",
      "slug": "qwen"
    },
    "quantizedBy": {
      "name": "MLX Community",
      "slug": "mlx-community"
    }
  },
  "device": {
    "cpu": "Apple M1 Ultra",
    "cpuCores": 20,
    "gpu": "Apple M1 Ultra",
    "gpuCores": 48,
    "gpuCount": 1,
    "ramGb": 64,
    "osName": "macOS",
    "osVersion": "26.4.1"
  },
  "decodeTpsMean": 47.1,
  "prefillTpsMean": 648.5,
  "ttftP50Ms": 6319.1,
  "idleTpsMean": 4051,
  "peakRssMb": 46080,
  "trialsPassed": 10,
  "trialsTotal": 10,
  "runnabilityScore": 0.48550000000000004,
  "bundleSha256": "0ee27d3c30028eb73982e50ee92d5113fb4660775f74360a03beb18d671e0d8d",
  "createdAt": "2026-04-14T03:55:14.441Z"
}