3 articles tagged Houtini LM.
The question I get asked is which local model is best for coding. Wrong question. The setup that works routes three tiers - Claude reasons, Kimi builds, and a Qwen coder on my own rig does the volume for nothing. Here's the whole thing, wired up.
· claude-code · local-llm
I decommissioned Hopper (my local LLM bootstrapped server) and moved my local models to a two-card 4090 rig with vLLM on Docker. It's so much faster - but houtini-lm spat its dummy. Two bugs, one hiding behind the other, and how v3.2.1 fixes it.
· claude-code · mcp
I left Claude Code running overnight a few months back and winced at the token bill - most of it spent on work any competent model could handle. So I built Houtini LM: Claude stays the architect and the QA, a cheap local model does the drafting, and the bill drops as a side-effect. In today's post I'm showing how I run it on my own rig, what I delegate, and where it falls down.
· claude-code · openrouter