Deploying NemoClaw with Qwen3.5-27B locally via Telegram for secure, cost-free inference.

Deploy & Ops📅 2026/03/26
Source@NielsRogge
#Developer#Fully Automatic#Low Risk#Manual Trigger#Reusable#Telegram#代码仓库#安全沙箱#报告#本地部署
NemoClaw security sandbox managing Qwen3.5-27B local inference on DGX Spark via Telegram interface
So cool!!

I'm running @nvidia's NemoClaw with Qwen3.5-27B entirely locally via Telegram. No API costs, no data being sent to anyone

NemoClaw is a security sandbox built on top of @openclaw that lets you restrict the files and networks your lobster can access.

I'm running the 4-bit GGUF via llama cpp on a DGX Spark. It's running pretty smoothly at 9 tokens per second!

The future might be local :)