Local AI Guide

See the speed before choosing hardware

Prefill and token generation speed

Studio M4 Max 128GB with Qwen3.6 35B-A3B (MoE): prefill and generation speed

Last updated

546 GB/s
Active 3B / Total 35B
39.2 ~ 81.9 tok/sDecode speed
Model fully loaded (21.28GB / 114GB)
First token (TTFT)
1.5 ~ 3.1 sContext 4,096 input tokens included
Prefill speed
1,316 ~ 2,751 tok/s1.5 ~ 3.1 s (Benchmark-calibrated)
Total time (E2E)
Approximately 2.9 to 6.1 seconds117 output tokens included
Press Play to process the input and generate the answer.
Ready
Expand settings 4-bit · 4K · Baseline decode
QuantizationNeed 21.28GB
Input context4K tokens
Baseline
Baseline
Sample question:
117 output tokens

Check configuration

Studio M4 Max 128GB · Memory 128GB

Qwen3.6 35B-A3B (MoE) Q4_K_M configuration. Check that the retailer lists the same memory option.

Already own it? Open the setup guide

Would another device feel faster?

Compare the same model including prefill, or just token generation.

What changes with a longer document?Expand input length, waiting time, speed and memory
Detailed analysis and all 60 hardware configurations

Popular configurations

Speed simulations by device and model

View all 20

Mac mini M4 Pro 64GB × Qwen3.6 35B-A3B (MoE)

19.6 ~ 46.1 tok/s · 2.7 ~ 6.3 s

DGX Spark 128GB × Qwen3.6 35B-A3B (MoE)

61.2 ~ 111.1 tok/s · 1.5 to 3.1 seconds

2× RTX 3090 48GB (NVLink) × Qwen3.6 35B-A3B (MoE)

79.2 ~ 248.6 tok/s · 0.63 to 1.4 seconds

Qwen3.8 27B on Mac Studio M4 Max 128GB

27.9 ~ 60.4 tok/s · 5.8 to 10.5 seconds