• token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
• context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.

Qwen3.8-27B runs locally in about 17GB and is already packaged in LM Studio, putting a current-generation open-weights model within reach of a single well-specced laptop.

• postQwen3.8-Flash goes live on OpenRouter
• postYes, we are back👑, with 206 tok/s on a single RTX 5090! Amazing Day-0 work from
• postQwen3.8-Flash API goes live with 262K context and $0.016 cache reads
• repoThank you @NVIDIAAI for the day-0 support! 🙌 Developers can finetune the model…

• postQwen 3.8 27B weights are coming out next week. It's a big deal.Alex Cheema
• articleQwen 3.8 27B is excellent, but it defaults to wildly overthinking thingssimonwillison.net
• articleQwen2.5-LLM: Extending the boundary of LLMsQwen Team

Checking sign-in…

Loading comments…