Qwen
MLX Community

Qwen3.6-35B-A3B benchmark on an Apple's logo.M5 Pro · 64 GB

<- Runs

Prompt tokens

40,960

Generation tokens

10,240

Trials passed

10/10

Verified

95.8 tok/s

2,360.1 tok/s

Peak memory

21.00/64 GB

Runs well

Trials

Decode / Prefill Speeds

Metadata

metadata.json
{
"runId": "run_3c594670-6d6f-4f4b-87a1-f9ff4460a44d",
"bundleId": "mlx-qwen3.6-35b-a3b-nvfp4-2b848b",
"status": "verified",
"promptTokens": 40960,
"completionTokens": 10240,
"contextLength": 5120,
"harness": {
"version": "0.1.22",
"gitSha": "ff1d570"
},
"runtime": {
"name": "mlx_lm",
"version": "0.31.3",
"buildFlags": null
},
"model": {
"displayName": "Qwen3.6-35B-A3B",
"format": "mlx",
"quant": "nvfp4",
"architecture": "qwen3_5_moe",
"source": "mlx-community/Qwen3.6-35B-A3B-nvfp4",
"fileSizeBytes": 20402144306,
"lab": {
"name": "Qwen",
"slug": "qwen"
},
"quantizedBy": {
"name": "MLX Community",
"slug": "mlx-community"
}
},
"device": {
"cpu": "Apple M5 Pro",
"cpuCores": 18,
"gpu": "Apple M5 Pro",
"gpuCores": 20,
"gpuCount": 1,
"ramGb": 64,
"osName": "macOS",
"osVersion": "26.4.1"
},
"decodeTpsMean": 95.8,
"prefillTpsMean": 2360.1,
"ttftP50Ms": 1758.94,
"idleTpsMean": 19456,
"peakRssMb": 21504,
"trialsPassed": 10,
"trialsTotal": 10,
"runnabilityScore": 0.8120775,
"bundleSha256": "edcb17727f521bf1e72f5614fd1d0d8595341469368c3092fc04c8d5ddeb5818",
"createdAt": "2026-04-23T00:18:32.770Z"
}