Skip to content
Andrew Voirol
WorkLogAboutContact
HomeWorkLog

AboutContact

✦ Just one prompt away from figuring it all out.

Sunday, April 12, 2026openclaw-pipeline

From benchmarks to bots: ClawdyDawdy lives

OpenClawTelegramAgenticReflections

For weeks I've been running synthetic benchmarks to see if a 2017 iMac can handle 30B parameter LLMs. The answer was yes, but benchmarks are boring. Today I wired up OpenClaw to my local Vulkan-accelerated llama-server and built a Telegram bot named ClawdyDawdy. It works. The e4b model at 24 tok/s is fast enough for conversational fluid responses, and handles tool-calling flawlessly. We're no longer just testing models, we're building autonomous agents that text me from a 9-year-old desktop.

← Previous

The subagent revelation & tiered routing

Next →

The MoE bug nobody told me about


Andrew Voirol

Builder, hacker, shipper. Currently leaving localhost.

Navigate

WorkBuilder’s LogAboutContactRSS Feed

Connect

X / TwitterGitHubLinkedIn

© 2026 Andrew Voirol✦Just one prompt away from figuring it all out.