Bionic by LM Studio: An Agent App for Local Models

Melvin Vivas · X post · 2026-09-12 · Open on X

Topics: AI Agents, Tool Use & MCP, AI Dev Tools & Productivity, LLMOps, Deployment & Monitoring · Level: intermediate

Summary

LM Studio has released Bionic, a new agent app that works with models running locally. The creator plans to try it with Qwen3.8 27B on an RTX 3090. This setup lets you run agents without cloud APIs.

Key points

Bionic is LM Studio's new agent app.
It works with models running locally.
The creator's planned setup is Qwen3.8 27B on one RTX 3090 GPU (24 GB).

Resources mentioned

Bionic · tool · lmstudio.ai · free
A tool the creator says the open-sourced style model could be used with.
Also in: Idea: Fine-Tune a Small Model on Your Best Tweets (Melvin Vivas on X · notes)
LM Studio · tool · x.com · free
Desktop app for downloading and running LLMs locally, with a developer mode that serves models through an API.
Also in: Running LLMs Locally Without an Expensive Rig (Melvin Vivas on X · notes), Adding Vercel AI Gateway as a provider in AIBackends with Devin (Melvin Vivas on X · notes), LoRA Fine-Tune Qwen3.5-2B on Your Tweets with Unsloth Studio (Melvin Vivas on X · notes), AIBackends: An API Layer Between Your App and AI Models (Now with Jev) (Melvin Vivas on X · notes) and 31 more
Qwen3.8-27B · tool · huggingface.co · free
A 27B-parameter open-weight model from Alibaba's Qwen family that you can run locally or call through hosted APIs.
Also in: Deploying Qwen3.8 27B on Hugging Face Inference Endpoints (Melvin Vivas on X · notes), Using Hugging Face credits: Jobs, Inference Endpoints and Open Models (Melvin Vivas on X · notes), Running Qwen3.8-27B Locally on an M5 Max MacBook with Inco Splash (Melvin Vivas on X · notes), Ternary Bonsai 2 27B: 9x smaller model keeping 98.2% of benchmark scores (Melvin Vivas on X · notes) and 24 more

Try this

Try Bionic with a local model, such as Qwen3.8 27B on a 24 GB GPU.
Run a fully local agent setup with LM Studio Bionic and Qwen3.8 27B.