cd /news/large-language-models/lm-studio-adds-glm-5-3-flash-to-bion… · home topics large-language-models article
[ARTICLE · art-112498] src=9to5mac.com ↗ pub= topic=large-language-models verified=true sentiment=↑ positive

LM Studio adds GLM-5.3-Flash to Bionic, with image support and 1M-token context

LM Studio has added Z.ai's GLM-5.3-Flash model to Bionic, its AI agent platform for Mac and Windows, bringing multimodal input, a 1-million-token context window, and pricing up to 10 times cheaper than GLM-5.2. The 320-billion Mixture-of-Experts model with 18 billion active parameters scores ahead of GLM-5.2 on benchmarks and is available via cloud with zero-data-retention policy.

read2 min views1 publishedAug 27, 2026
LM Studio adds GLM-5.3-Flash to Bionic, with image support and 1M-token context
Image: 9To5Mac (auto-discovered)

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 moves fast to add GLM-5.3-Flash to Bionic #

Since its original announcement in mid-July, LM Studio has been steadily expanding the models and capabilities available in Bionic, its Mac and Windows platform for agentic tasks such as coding, research, and working with documents and files.

LM Studio Bionic can use either locally run models or cloud models hosted on US-based servers, with the latter covered by a strict zero-data-retention policy.

Shortly after launching LM Studio Bionic, the company added support for Moonshot AI’s Kimi K3. Today, the company rolled out cloud support for Z.ai’s new GLM-5.3-Flash model, which LM Studio says is up to 10 times cheaper to run than GLM-5.2.

LM Studio’s announcement came just hours after the official unveiling of GLM-5.3-Flash, which had already generated plenty of buzz while being anonymously tested on OpenCode and OpenRouter under the codename “Ox Alpha.”

GLM-5.3-Flash is a 320-billion Mixture-of-Experts model with 18 billion active parameters, supports image and text inputs, and has a 1-million-token context window.

It scores ahead of GLM-5.2 across the benchmarks highlighted by Z.ai, while generally falling within the same range as frontier models from Anthropic, OpenAI, Google, and DeepSeek.

To learn more about how you can use GLM-5.3-Flash on LM Studio Bionic, follow this link. 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 NeoLogitech MX Master 4AirPods Pro 3AirTag (2nd Generation) – 4 PackApple Watch Series 11Wireless CarPlay adapter

*FTC: We use income earning auto affiliate links.* [More.](https://9to5mac.com/about/#affiliate)

[our homepage](http://9to5mac.com/)for all the latest news, and follow 9to5Mac on

[exclusive stories](https://9to5mac.com/feature/exclusive/),

[reviews](https://9to5mac.com/guides/review/),

[how-tos](https://9to5mac.com/guides/how-to/), and

[subscribe to our YouTube channel](https://www.youtube.com/9to5mac)
── more in #large-language-models 4 stories · sorted by recency
── more on @lm studio 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/lm-studio-adds-glm-5…] indexed:0 read:2min 2026-08-27 ·