You can use your Core to power inference in other apps and custom harnesses like OpenCode, OpenClaw, and Hermes. Core reaches over 87 tok/s on Qwen-3.8-27B and 32 tok/s on Qwen-3.8-Next.

Name: You can use your Core to power inference in other apps and custom harnesses like OpenCode, OpenClaw, and Hermes. Core reaches over 87 tok/s on Qwen-3.8-27B and 32 tok/s on Qwen-3.8-Next.
Channel: Zain Javaid
Description: You can use your Core to power inference in other apps and custom harnesses like OpenCode, OpenClaw, and Hermes. Core reaches over 87 tok/s on Qwen-3.8-27B and 32 tok/s on Qwen-3.8-Next.

@Zain Javaid

1 grabs

Download

You can use your Core to power inference in other apps and custom harnesses like OpenCode, OpenClaw, and Hermes. Core reaches over 87 tok/s on Qwen-3.8-27B and 32 tok/s on Qwen-3.8-Next.

No comments yet