LM Studio adds GLM-5.3-Flash to Bionic with 1M-token context
LM Studio has added Z.ai's GLM-5.3-Flash to Bionic, bringing image support, a 1M-token context, and up to 10x lower cloud pricing than GLM-5.2.
The integration expands Bionic's roster of cloud-hosted models, which also includes Moonshot AI's Kimi K3. Bionic is designed for agentic tasks such as coding, research, and working with documents and files, and can run models locally or on US-based servers with a zero-data-retention policy.
LM Studio's announcement came just hours after Z.ai formally unveiled GLM-5.3-Flash, a model that had already generated attention while being anonymously tested on OpenCode and OpenRouter under the codename "Ox Alpha." According to LM Studio, running GLM-5.3-Flash in Bionic costs up to 10 times less than GLM-5.2.
GLM-5.3-Flash is a 320-billion-parameter mixture-of-experts model with 18 billion active parameters. It accepts both image and text inputs and supports a 1-million-token context window. On benchmarks highlighted by Z.ai, the model scores ahead of GLM-5.2 and broadly falls within the same range as frontier models from Anthropic, OpenAI, Google, and DeepSeek.
No further details were provided about local execution support or future enhancements. LM Studio has been steadily expanding Bionic's model lineup since its mid-July launch.