LM Studio’s agentic workflow platform now lets users run tasks with Kimi K3, Moonshot AI’s 2.8-trillion-parameter model with a 1-million-context window. Here are the details.
Kimi K3 now available on LM Studio Bionic
A few days ago, LM Studio announced Bionic, a new app aimed at users looking to leverage open models for agentic tasks.
Bionic is designed to handle coding, research, and more complex work involving creating or editing documents and files.
Users can run models locally or, when a task requires more computing power, leverage larger cloud-based open-source models that offer longer context windows, and stronger reasoning and tool-calling capabilities that smaller, local models can’t offer (yet).
From LM Studio’s original announcement:
Bionic is the AI agent for getting real work done with open models, including coding, research, and complex work with documents and files. You can use local models or switch to open-source models in the cloud for heavier tasks, all while staying in control of your privacy and AI spend.
For cloud-based models, Bionic relies on US-based inference with Zero Data Retention. This means that requests are processed on servers in the United States, and that prompts, files, and model outputs are not stored after processing is complete.
Up until now, users relying on cloud-based open models could use DeepSeek V4, Pro, GLM-5.2, Kimi K2.6, and Kimi-K2.7-Code. Today, the company added Kimi K3, giving users access to what many consider the most capable open-source model currently available.
Through Bionic, Kimi K3 is priced at $3 per million input tokens, $0.30 per million cached input tokens, and $15 per million output tokens.
That is a stark contrast to the models previously available, which ranged from $0.95 to $.174 per million input tokens and from $3.48 to $4.50 per million output tokens.
That said, the addition of Kimi K3 is a welcome development, particularly for users looking to tackle more challenging tasks through LM Studio Bionic.
LM Studio Bionic is available for Mac and Windows, and you can learn more about it here.
Do you run local models on your Mac? Let us know in the comments.
Worth checking out on Amazon
- Geoffrey Cain – ‘Steve Jobs in Exile’
- David Pogue – ’Apple: The First 50 Years’
- MacBook Neo
- Logitech MX Master 4
- AirPods Pro 3
- AirTag (2nd Generation) – 4 Pack
- Apple Watch Series 11
- Wireless CarPlay adapter