Repository: localaiLicense: apache-2.0
UI-Mate-9B is Tencent's 9B-parameter multimodal computer-use agent, fine-tuned from Qwen3.5-9B. It accepts task instructions, screenshots, and interaction history, then emits reasoning and structured mouse and keyboard actions for long-running desktop tasks. The model requires an external runtime to execute its actions and should run with human confirmation for sensitive operations. This entry uses the recommended Q4_K_M GGUF quantization.
Links
Tags
Repository: localaiLicense: apache-2.0
UI-Mate-9B is Tencent's 9B-parameter multimodal computer-use agent, fine-tuned from Qwen3.5-9B. It accepts task instructions, screenshots, and interaction history, then emits reasoning and structured mouse and keyboard actions for long-running desktop tasks. The model requires an external runtime to execute its actions and should run with human confirmation for sensitive operations. This entry uses the higher-quality Q8_0 GGUF quantization.
Links
Tags
Repository: localaiLicense: mit
Fara1.5-4B is Microsoft's 4B-parameter multimodal computer-use agent for web browsers, fine-tuned from Qwen3.5-4B. It accepts screenshots and text, emits structured browser actions, supports a 262K-token context, and should be deployed with appropriate sandboxing and user-confirmation controls. This entry uses the recommended Q4_K_M GGUF quantization.
Links
Tags
Repository: localaiLicense: mit
Fara1.5-4B is Microsoft's 4B-parameter multimodal computer-use agent for web browsers, fine-tuned from Qwen3.5-4B. It accepts screenshots and text, emits structured browser actions, supports a 262K-token context, and should be deployed with appropriate sandboxing and user-confirmation controls. This entry uses the higher-quality Q8_0 GGUF quantization.
Links
Tags
Repository: localaiLicense: mit
Fara1.5-9B is Microsoft's 9B-parameter multimodal computer-use agent for web browsers, fine-tuned from Qwen3.5-9B. It accepts screenshots and text, emits structured browser actions, supports a 262K-token context, and should be deployed with appropriate sandboxing and user-confirmation controls. This entry uses the recommended Q4_K_M GGUF quantization.
Links
Tags
Repository: localaiLicense: mit
Fara1.5-9B is Microsoft's 9B-parameter multimodal computer-use agent for web browsers, fine-tuned from Qwen3.5-9B. It accepts screenshots and text, emits structured browser actions, supports a 262K-token context, and should be deployed with appropriate sandboxing and user-confirmation controls. This entry uses the higher-quality Q8_0 GGUF quantization.
Links
Tags
Repository: localaiLicense: mit
Fara1.5-27B is Microsoft's 27B-parameter multimodal computer-use agent for web browsers, fine-tuned from Qwen3.5-27B. It accepts screenshots and text, emits structured browser actions, supports a 262K-token context, and should be deployed with appropriate sandboxing and user-confirmation controls. This entry uses the Q4_K_M GGUF quantization.
Links
Tags
Repository: localaiLicense: mit
Fara1.5-27B is Microsoft's 27B-parameter multimodal computer-use agent for web browsers, fine-tuned from Qwen3.5-27B. It accepts screenshots and text, emits structured browser actions, supports a 262K-token context, and should be deployed with appropriate sandboxing and user-confirmation controls. This entry uses the Q8_0 GGUF quantization.
Links
Tags