This path is for you if the names of open models have started to blur together. It separates a base model, a fine-tune, an instruct variant, and a small model you can run. No part is live on this page yet. Start with Open-source AI explained, which already covers weights, licenses, and a model card.
- 1 Base, fine-tuned, or instruct: which kind of open AI model to download Map open models as foundations, fine-tunes, and instruct variants. Read the model card and license before you pin a default. Thumbnails are not architecture. Scheduled · November 20, 2026
- 2 A guide to small open AI models: Mistral, Gemma, Phi, and Qwen Use a short map of Mistral, Gemma, Phi, and peers to pick roles. Avoid the release-note dump. One default beats a sticker wall. Scheduled · November 22, 2026
- 3 Code Models You Can Run Yourself: Qwen, DeepSeek, and More Treat code-tuned open models as assistants with a verify step. Keep unit tests and human review in the loop. Specialization is not a license to skip diffs. Scheduled · November 24, 2026
- 4 Small Models That Actually Run Offline Pick small quantized models for offline and edge work. Match RAM and power first. Do not expect cloud-sized prose from a pocket-sized weight file. Scheduled · November 26, 2026
- 5 Why your team should standardize on one open AI model, like Qwen or Llama Choose one default open-model stack and stick to it through a real upgrade gate. Model hopping taxes prompts, tooling, and delivery more than it buys accuracy. Scheduled · November 28, 2026
- 6 Which AI benchmark scores to ignore, and the few worth trusting Ignore vanity benchmarks as buying guides. Keep a few high-signal public checks if you must, and invest in an internal golden harness tied to your prompts. Scheduled · November 30, 2026