prompt is too long: 16535 tokens > 8221 maximum

[ppscia]

Before you start

• I have read the FAQ and my problem is not answered there.
• I have read the Roadmap and this is not already planned there.
• I have searched existing issues and found no duplicate.
• I have restarted the Desktop app to pick up the latest update and the problem still happens.

What happened

运行失败
prompt is too long: 16535 tokens > 8221 maximum (prompt + generation); shorten the prompt or increase the KV cache budget

Desktop app version

最新

OS

Windows 10

OS details

No response

GPU and driver

3060，8G显存

CPU and system RAM

14600，64G

Checkpoint

qwen3.6-35B-A3B NVFP4

Model settings

No response

Engine log

Anything else

No response

[jason-fxz]

In Console -> Cache Config, you can scale up KV Cache.

[ppscia]

In Console -> Cache Config, you can scale up KV Cache.
I couldn't find the "Cache Config" you mentioned. Could you provide a screenshot?