Jackrong

Qwen3.5-27B (Claude Opus 4.6 Distill) benchmark on an Apple's logo.M4 Max · 128 GB

<- Runs

Prompt tokens

40,960

Generation tokens

10,240

Trials passed

10/10

Verified

8.6 tok/s

227.8 tok/s

Peak memory

54.00/128 GB

Runs poorly

Trials

Decode / Prefill Speeds

Metadata

metadata.json
{
"runId": "run_673c9975-2688-4195-9a92-ac8a852e0968",
"bundleId": "mlx-qwen3.5-27b-claude-4.6-opus-reasoning-di-038955",
"status": "verified",
"promptTokens": 40960,
"completionTokens": 10240,
"contextLength": 5120,
"harness": {
"version": "0.1.18",
"gitSha": "c71d7d8"
},
"runtime": {
"name": "mlx_lm",
"version": "0.31.2",
"buildFlags": null
},
"model": {
"displayName": "Qwen3.5-27B (Claude Opus 4.6 Distill)",
"format": "mlx",
"quant": "bf16",
"architecture": "qwen3_5",
"source": "Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled",
"fileSizeBytes": 55563022432,
"lab": {
"name": "Jackrong",
"slug": "jackrong"
},
"quantizedBy": null
},
"device": {
"cpu": "Apple M4 Max",
"cpuCores": 16,
"gpu": "Apple M4 Max",
"gpuCores": 40,
"gpuCount": 1,
"ramGb": 128,
"osName": "macOS",
"osVersion": "26.4"
},
"decodeTpsMean": 8.6,
"prefillTpsMean": 227.8,
"ttftP50Ms": 17937.77,
"idleTpsMean": 52224,
"peakRssMb": 55296,
"trialsPassed": 10,
"trialsTotal": 10,
"runnabilityScore": 0.3286297619047619,
"bundleSha256": "704f48a41cfd83d44bb8c1c2e70be3cbbbda75d02bbdbad4951bc9f8ea67ea2f",
"createdAt": "2026-03-31T18:20:02.066Z"
}