Posts tagged "llm"

September 2026

• Grounding a coding agent in reality

August 2026

• Running Qwen 3.8 27B on a 16 GB GPU
• Claude Code - Using Context More Efficiently
• Kimi K3's cache discount doesn't survive OpenRouter

July 2026

• Every LLM tool call re-sends your entire conversation
• Switching my local LLM to Qwen 3.6, a 35B Mixture-of-Experts model, on a 16 GB GPU

March 2026

• Switching Open WebUI from Ollama to llama.cpp for Qwen 3.5

All tags