WooBee AI

WebLLM Async Processor & Webhook Router

Model Manager

Active Engines

Select Model (Under 16GB RAM)

Llama 3.2 1B (Instruct)

Llama • 879 MB

Not Cached

Models Cache Overview

Llama 3.2 1B (Instruct)879 MB • 0.9 GB VRAM

Not Cached

Llama 3.2 3B (Instruct)2.2 GB • 2.3 GB VRAM

Not Cached

Llama 3 8B (Instruct)4.3 GB • 4.9 GB VRAM

Not Cached

Llama 3.1 8B (Instruct)4.6 GB • 4.9 GB VRAM

Not Cached

DeepSeek R1 Distill Llama 8B4.7 GB • 4.9 GB VRAM

Not Cached

Qwen 2.5 0.5B (Instruct)945 MB • 1.0 GB VRAM

Not Cached

Qwen 2.5 1.5B (Instruct)1.6 GB • 1.6 GB VRAM

Not Cached

Qwen 2.5 3B (Instruct)2.5 GB • 2.5 GB VRAM

Not Cached

Qwen 2.5 7B (Instruct)4.7 GB • 5.0 GB VRAM

Not Cached

Qwen 2.5 Coder 7B (Instruct)4.7 GB • 5.0 GB VRAM

Not Cached

DeepSeek R1 Distill Qwen 7B4.7 GB • 5.0 GB VRAM

Not Cached

Gemma 3 1B (Instruct)711 MB • 0.7 GB VRAM

Not Cached

Gemma 2 2B (Instruct)1.9 GB • 1.9 GB VRAM

Not Cached

Gemma 2 9B (Instruct)5.5 GB • 6.3 GB VRAM

Not Cached

Queue Pending0

Throughput (Speed)--

Avg Latency--

Total Processed0

Active Processors

Initialize local LLM from the Model Manager to begin queue loop.

Dashboard System Logs

Terminal ready. Systems normal.

Queue History (Max 30 Completed Items Threshold)

Automatically prunes completed list to 30 items

No jobs currently in queue history.

Real-time Outbound Webhook Logs

Timestamp	Job ID	Destination URL	Status	Delivery
No outbound webhook transmissions logged yet.