#Self-Hosting

PewDiePie says OpenAI banned his account twice for distillation while he was training Ajax, a local Qwen 3.5 9B with refusals removed by Heretic. What model distillation is, how OpenAI detects it (the report on the Moonshot case came out two days earlier), what's inside Ajax, and where the line sits between legitimate synthetic data and a ban on your account.

Jev costs US$0.042 per million tokens and is a closed API. Laya is Apache 2.0, runs offline on a 2018 GPU and measures 7.8x faster at P50. A comparison with the numbers each side published, the prior-art fight that broke out on Hacker News, and the October update: Cloudflare's open-weight Clef and OpenAI's Decisions API on GPT-6 Luna.

Alibaba shipped Qwen 3.8 27B and someone opened the diff against 3.6: 59 of 59 graph nodes map one-to-one, and the only differing field is metadata. Same architecture, DeepSWE tripling from 13.3 to 42.2. Here are the real benchmarks (and what the vendor table leaves out), the VRAM math the press oversimplified, the 64KB-per-token KV cache, the Jinja template bug that kills tool calls on day 1, and the difference between the dense 27B and the 2.4T 3.8 Max. With the counterpoint nobody made.

Alibaba is publishing the weights of Qwen3.8-Max, 2.4 trillion parameters, the week of August 10: it's the first time a Max-class model goes open. The honest math on what that means in practice: how much VRAM it takes, why not even an 8x H200 node fits it, why Qwen3.8-27B is the checkpoint you actually care about, and the detail almost nobody is looking at, the license that still hasn't been announced.

A step-by-step guide to running an LLM locally with Ollama: install it, run qwen3:8b in 2 commands, and plug it into your code through the OpenAI-compatible endpoint. It runs on 8 GB of RAM with no GPU required. As a bonus, the VRAM math by model size and when local beats the API.