A coding agent on your own model: OpenCode, Qwen Code and more
This story is from 2026-11-16. It is preserved in the archive; the latest stories are on the live feed.
A coding agent on your own model needs a GPU with 24 GB or more, a context of at least 64 thousand tokens and a model that can call tools. Qwen 3.8 27B at a 64K context takes 20.7 GB by our calculation, and Qwen3 Coder 30B-A3B takes 24.3 GB. Below: which agents work with a model that is not theirs,…
Read the full story at DEV Community — AI ↗
Timeline · 1 report
- 2026-11-16 16:42 · DEV Community — AI
A coding agent on your own model: OpenCode, Qwen Code and more
More stories
- How to Speed Up Qwen3.8-27B in llama.cpp (NVIDIA's Draft Model May Lose to MTP) — DEV Community — Machine Learning
- Qwen4-Max Cuts AI Task Costs, but Gives Up Qwen’s Open-Model Edge — DEV Community — AI
- RadixArk opens DaisyRose-27B, an agent-tuned Qwen model — DEV Community — AI
- Run Mobilerun with local and cheap models Ollama, DeepSeek, Qwen, OpenRouter — DEV Community — Machine Learning
- An attached file told the model to delete all customers. In OpenWebUI, it tried — DEV Community — AI
- RadixArk Doubles A Free AI Model's Coding Score In Just 18 Days — DEV Community — Machine Learning
- Qwen Image: Wan2.1 flf2v — 2 Workflows, Read From the Graphs — DEV Community — AI
- The 12-Day Open-Source Pledge: Alibaba Locks Qwen4-Max Behind a Closed API — DEV Community — Machine Learning
Read the Daily Brief: the day's most important AI stories →