LM Studio adds GLM-5.3-Flash to Bionic, with image support and 1M-token context
LM Studio has added Z.ai’s new GLM-5.3-Flash model to Bionic, its AI agent platform, bringing multimodal input, a 1 million-token context window, and significantly lower pricing than GLM-5.2. Here are the details.
LM Studio has integrated Z.ai's GLM-5.3-Flash model into its Bionic AI agent platform, adding multimodal input support, a 1 million-token context window, and reduced pricing compared to GLM-5.2. The platform, targeting Mac and Windows users for agentic tasks like coding and document handling, can now utilize cloud or locally-run models with strict zero-data-retention policies on US-based servers.
GLM-5.3-Flash, a 320-billion Mixture-of-Experts model with 18 billion active parameters, supports both image and text inputs. It has scored above GLM-5.2 in benchmarks set by Z.ai, while generally matching the performance levels of models from Anthropic, OpenAI, Google, and DeepSeek. For more information on integrating GLM-5.3-Flash with LM Studio Bionic, users can visit a provided link.
The company encourages readers to share their experiences using local models on Mac devices in the comments section.
Written by urgent.news from 9to5Mac's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
