@infinitemonkey
About
Nothing here yet.
Available for
Nothing here yet.
Artem Kunyk's blogs
Recently published
Lunapark: Building a Minimalistic Rust Agent on Qwen 3.6
Apr 23 · 17 min read · Local AI agents are exploding across the developer ecosystem. Every week a new framework appears promising to simplify agent construction, and every week it ships with hundreds of transitive dependencies, a Python runtime, and startup times measured ...
Join discussionBuilding Lunapark: A Local Autonomous Agent on 7.3 MB and Zero API Costs
Apr 10 · 17 min read · It was late February 2026. A $2.18 charge appeared on the Azure billing dashboard — overnight LLM API calls from an experimental autonomous coding agent. The amount was irrelevant. The thought that followed was not: "This agent should own its own co...
Join discussionReasoning Models Don't Fail at Reasoning: The Protocol Layer Is What Kills Local Agents
Apr 5 · 6 min read · Reasoning Models Don't Fail at Reasoning: The Protocol Layer Is What Kills Local Agents April 5, 2026 · Artem The narrative around local LLMs stops at the model checkpoint. It never discusses what breaks between the model and the tool call. I ran mi...
Join discussionTurboQuant Is Not a Free Lunch: What the RTX 3060 Actually Reported
Apr 3 · 8 min read · TurboQuant Is Not a Free Lunch: What the RTX 3060 Actually Reported April 3, 2026 · Artem The ternary quantization narrative is being sold as a compression silver bullet. It isn't. On a 12 GB consumer GPU running Qwen-family models, a plain q8_0 GGU...
Join discussion