Local AI Guide

See the speed before choosing hardware

Prefill and token generation speed

Ryzen AI Max+ 395 128GB with Qwen3.8 27B: prefill and generation speed

Last updated

256 GB/s
27B
11.2 ~ 12.5 tok/sDecode speed
Model fully loaded (17.56GB / 96GB)
First token (TTFT)
46.6 to 85.4 secondsContext 4,096 input tokens included
Prefill speed
48 ~ 88 tok/s46.5 to 85.3 seconds (Specification-based estimate)
Total time (E2E)
Approximately 55.9 to 95.8 seconds117 output tokens included
Press Play to process the input and generate the answer.
Ready
Expand settings 4-bit · 4K · Baseline decode
QuantizationNeed 17.56GB
Input context4K tokens
Baseline
Baseline
Sample question:
117 output tokens

Check configuration

Ryzen AI Max+ 395 128GB · Memory 128GB

Qwen3.8 27B 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 61 hardware configurations

Popular configurations

Speed simulations by device and model

View all 20

Qwen3.8 27B on Mac mini M4 32GB: response speed

5.1 ~ 5.7 tok/s · 16.4 ~ 35.5 s

Qwen3.8 27B: is a Mac mini M4 Pro 48GB worth it?

12.3 ~ 13.7 tok/s · 7.8 ~ 14.3 s

Qwen3.8 27B on MacBook Pro M5 Pro 64GB

14.7 ~ 17.1 tok/s · 8.6 to 10.0 seconds

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

27.9 ~ 60.4 tok/s · 5.8 to 10.5 seconds