GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
aanandmodi
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
aanandmodi
Model Tree
Qwen/Qwen3-VL-2B-Instruct
Input Modalities
Output Modalities
Supported Functionality
Qwen/Qwen3-VL-2B-Instruct at immutable revision 89644892e4d85e24eaac8bacfd4f463576704203.BIFOLD-BigEarthNetv2-0/BigEarthNet.txt.lithuania-summer; 6,000 bounded training rows.0..1 coordinates to Qwen 0..1000.Use on RGB previews derived from optical imagery. Do not pass raw SAR or 12-band Sentinel tensors to this model. SatQuery routes those inputs to its TerraMind fusion specialist.
The training subset is European Sentinel imagery. Performance on Indian Cartosat/RISAT imagery is not established. Outputs require validation, evidence display, uncertainty labeling and abstention. Generated-token likelihood is not a calibrated probability of correctness.
json
{"rows": 120,"vqa_exact_match": 0.6,"grounding_mean_iou": 0.3620281495145568,"grounding_accuracy_iou_0_5": 0.4,"caption_token_f1": 0.35107449654793066,"proxy_ece_on_non_caption_rows": 0.24431528830364974}