Jackrong
MLX Community

Qwen3.5-27B (Claude Opus 4.6 Distill) benchmark on an Apple's logo.M4 Max · 64 GB

<- Runs

Prompt tokens

40,960

Generation tokens

10,240

Trials passed

10/10

Verified

17.3 tok/s

143.6 tok/s

Peak memory

18.00/64 GB

Runs poorly

Trials

Decode / Prefill Speeds

Metadata

metadata.json
{
"runId": "run_4498ca6d-6fb5-4ed2-85ef-c9651ba66a87",
"bundleId": "mlx-qwen3.5-27b-claude-4.6-opus-distilled-ml-be4950",
"status": "verified",
"promptTokens": 40960,
"completionTokens": 10240,
"contextLength": 5120,
"harness": {
"version": "0.1.18",
"gitSha": "unknown"
},
"runtime": {
"name": "mlx_lm",
"version": "0.31.1",
"buildFlags": null
},
"model": {
"displayName": "Qwen3.5-27B (Claude Opus 4.6 Distill)",
"format": "mlx",
"quant": "4bit",
"architecture": "qwen3_5",
"source": "mlx-community/Qwen3.5-27B-Claude-4.6-Opus-Distilled-MLX-4bit",
"fileSizeBytes": 15133043513,
"lab": {
"name": "Jackrong",
"slug": "jackrong"
},
"quantizedBy": {
"name": "MLX Community",
"slug": "mlx-community"
}
},
"device": {
"cpu": "Apple M4 Max",
"cpuCores": 16,
"gpu": "Apple M4 Max",
"gpuCores": 40,
"gpuCount": 1,
"ramGb": 64,
"osName": "macOS",
"osVersion": "26.3.1"
},
"decodeTpsMean": 17.3,
"prefillTpsMean": 143.6,
"ttftP50Ms": 29214.57,
"idleTpsMean": 15360,
"peakRssMb": 18432,
"trialsPassed": 10,
"trialsTotal": 10,
"runnabilityScore": 0.4610642857142857,
"bundleSha256": "c85cdecdf10a736c49ab5211c81936065cecfebc09ba6b2d1a7561da4f24fd0a",
"createdAt": "2026-04-03T05:56:19.371Z"
}