GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
p-doom
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
p-doom
Model Tree
Qwen/Qwen3-VL-8B-Instruct
Input Modalities
Output Modalities
Supported Functionality
Provide one chat message with 10 images sampled at 5 FPS. Each image should be preceded by a text label:
text
Frame F00: <image>Frame F01: <image>...Frame F09: <image>
The frame labels are text anchors in the message, not labels rendered into the image pixels.
The model emits only a JSON array:
json
[{"frame": "F02", "type": "MouseMove", "details": "120,45"},{"frame": "F03", "type": "MouseClick", "details": "Left"},{"frame": "F05", "type": "KeyPress", "details": "Cmd+S"},{"frame": "F07", "type": "MouseScroll", "details": "-150"}]
Action types:
KeyPress: key name with modifiers, e.g. Cmd+S, Enter, AMouseClick: Left, Right, or MiddleMouseMove: normalized dx,dy, where 1000 is full screen width/heightMouseScroll: normalized signed scroll magnitudeFrame attribution: if an effect first appears between F_K and F_{K+1}, report the action on F_K, the last pre-action frame.
Qwen/Qwen3-VL-8B-InstructThe model was trained on macOS productivity recordings. It can confuse OS-specific shortcuts such as Cmd vs Ctrl, and it only predicts actions that are visible or inferable from screen pixels at 5 FPS.