Shamal AI
Sandbox · Dashboard
Qwen3-VL · VLM
Falcon Perception 0.6B · Detect
In-Kingdom
LIVE · Qwen + Falcon
Models
VLM (reasoning)
Qwen3-VL-30B-A3B-Instruct · Novita
Qwen2.5-VL-72B-Instruct
Qwen2.5-VL-7B-Instruct
Detector
Falcon Perception 0.6B
Detection task
Segment
Detect
Inference settings
VLM temperature
0.10
VLM max tokens
512
Falcon max tokens
100
Falcon temperature
0.00
Max objects
8
Confidence ≥
0.35
Compute dtype
bfloat16
float32
Seed
Deployment
VLM provider
Novita / HF
Detector
Local GPU
Data residency
In-Kingdom
Languages
EN · AR
Price $/1M tok (in/out)
Price is an editable estimate for the cost readout — confirm Novita/HF rates before quoting.
CONSTRUCTION
—
Drop an aerial / drone frame here, click to upload,
or load a synthetic demo frame.
JPG · PNG · top-down site imagery works best
▶ Run
⌗ Load demo frame
↑ Upload
Sample frames · click to load
Pipeline · results
Run a query — Falcon detects, Qwen reasons,
and the answer lands here step by step.