Z.ai makes AutoGLM Phone 9B, an open-source vision-language chat model that takes text and image inputs and returns text outputs. It is designed to function as a mobile intelligent assistant, automating smartphone tasks by understanding on-screen content and generating sequences of actions.
Input
Output
Context
66K
Max Output
4K
Parameters
9B
Input Modalities
Output Modalities
Some values come from web research and may be incorrect. Report incorrect data
None the catalog can show from stated facts or measured scores.
Download 20.6 GB · Runs on vLLM v0.32.0 · 9 GGUF builds
Public resources
Specification sources
As of Nov 10, 2026.
Answered from the facts on this page, with their sources.
AutoGLM Phone 9B has a context window of 65,536 tokens and a maximum output of 4,096 tokens (source: Creator or provider API). A provider may serve less; Inferbase routes on what each provider serves.
Yes. AutoGLM Phone 9B is an open-weight model under the MIT license. You can download and self-host it within the license terms.
About 9B, read from the model's name. Z.ai has not published an exact count.
Strengths: Open weights under a permissive license (mit). Each is computed from the model's stated facts and benchmark results.
AutoGLM Phone 9B accepts Text and Image and produces Text. The Capabilities card lists the API features it supports, such as function calling and structured output.
No benchmark source has published a result for AutoGLM Phone 9B yet, so it is shown as unmeasured, not estimated.
Not on Inferbase Managed today. Add your own provider key or endpoint that serves AutoGLM Phone 9B, and Inferbase runs it on your account with the same routing and logs.
Z.ai has not published a parameter count for AutoGLM Phone 9B, so the catalog cannot compute its memory. The GPU planner can size it from a count you enter.
The model card of AutoGLM Phone 9B lists one language: Chinese. That is what Z.ai states; the catalog does not test language quality.
Start on the free plan with 5,000 requests a month, no card required.