Fanar

Models · QCRI · Qatar

World Summit AI 2025

Arabic-centric multimodal platform: Fanar Star and Prime LLMs plus speech and image models. Fanar 2.0 launched Dec 2025.

Released: 10 Dec 2024
Official source: Official source — arxiv.org (opens in a new tab on arxiv.org)
Date source: Date source — hbku.edu.qa (opens in a new tab on hbku.edu.qa)
Item last updated: Not documented yet
Added to Souq: Not recorded yet

Capabilities

Arabic and English text generationsource (opens in a new tab on arxiv.org)
Speech and voice generationsource (opens in a new tab on arxiv.org)
Culturally-adapted image generationsource (opens in a new tab on arxiv.org)
Dialectal Arabic speech recognitionsource (opens in a new tab on arxiv.org)
Specialized Retrieval-Augmented Generation (Islamic and Recency RAG)source (opens in a new tab on arxiv.org)

Site last checked: 12 Nov 2026

Details reviewed against the official source. Verification limits are noted in the description; items marked “unverified” are inferred only.