# Hugging Face — Falcon Perception

- Company: Hugging Face (huggingface.co)
- Announced: 2026-04-01T07:13:20+00:00
- Category: new-model
- Subject: Platform
- Models affected: Falcon Perception, Falcon OCR
- Source: https://huggingface.co/blog/tiiuae/falcon-perception
- Record: https://forck.live/items/1525-falcon-perception

TII introduces Falcon Perception, a 0.6B-parameter early-fusion Transformer for open-vocabulary grounding and segmentation, and Falcon OCR, a 0.3B-parameter OCR model. Falcon Perception achieves 68.0 Macro-F1 on SA-Co, beating SAM 3's 62.3. Falcon OCR achieves 80.3 on olmOCR and 88.6 on OmniDocBench with high throughput. They also introduce PBench, a diagnostic benchmark.

## Evidence

Verbatim from https://huggingface.co/blog/tiiuae/falcon-perception:

> Falcon Perception is a 0.6B-parameter early-fusion Transformer for open-vocabulary grounding and segmentation from natural language prompts. The model processes image patches + text in one sequence using a hybrid attention mask, and produces variable numbers of instances with a small, structured token interface and lightweight output heads. On SA-Co, Falcon Perception reaches 68.0 Macro-F1 (vs. 62.3 for SAM 3) with the main remaining gap being presence calibration (MCC 0.64 vs. 0.82). We also introduce PBench, a diagnostic benchmark that breaks down performance by capability (attributes, OCR-guided disambiguation, spatial constraints, relations) and by dense long-context crowded scenes. We also relase Falcon OCR, a 0.3B-parameter model which reaches a score of 80.3 and 88.6 on the olmOCR benchmark and OmniDocBench respectively, while having the highest throughput of any open source OCR model.

---

Record: https://forck.live/items/1525-falcon-perception
Catalogue: https://forck.live/llms.txt
Feed: https://forck.live/feed.md