AI models tested for Arabic

Frontier Arabic model announced by HUMAIN at LEAP Riyadh on 3 Sept 2026: a 428B-parameter mixture-of-experts model on the MiniMax-M3 lineage, further pretrained on more than one trillion tokens of Arabic-native content. Commissioned by HUMAIN and delivered by MiniMax. As of 10 Sept 2026 it is research preview only — reachable through HUMAIN Node's playground and an OpenAI-compatible endpoint, with no weights published. HUMAIN says it expects to release weights under the MiniMax Community License after safety training, targeted for October 2026.

Small native-Arabic GPT models for research from the Saudi ArabianLLM initiative, published at 0.1B, 0.3B, 0.8B and 1.5B with task-tuned QA, summarisation and sentiment variants. Research-scale rather than production: the flagship repo has not changed since Feb 2024.

Arabic-localised LLM family with cultural alignment, co-developed by KAUST and King Abdulaziz University with CUHK-Shenzhen and SRIBD. Version 2 ships base and chat variants at 8B, 32B and 70B. The repos have not been updated since Nov 2024 and there is no v3.

Small Arabic/English model built in Khobar by injecting Arabic into an existing English model rather than pretraining from scratch; it is the base for both Mutarjim and Lahjawi. Misraj publishes its datasets and evaluation code openly but has released no Kuwain weights — the Hugging Face Misraj org hosts datasets only, and the model is reached through Misraj's Kawn platform.

Compact model tuned for Arabic/English RAG question-answering and entity extraction. Gemma-derived, so it ships under the Gemma Terms of Use; GGUF and 4-bit builds are published alongside it.

Gemma-based Arabic model that topped open Arabic rankings, outperforming much larger models. Because it is built on Gemma it inherits Google's Gemma Terms of Use rather than a standard open-source licence.

Largest model in the ALLaM family. SDAIA introduced the ALLaM family; HUMAIN adopted the 34B model and deployed it as the closed HUMAIN Chat service (Aug 2025). No weights, technical report or public API have been released, so there is no repository to link. An independent UI-level study evaluated it through HUMAIN Chat across MSA, five regional dialects and code-switching, but does not name those dialects.

Saudi national Arabic LLM built by the National Center for AI at SDAIA — 7B open weights, trained on 4T English tokens then 1.2T mixed Arabic/English tokens. The original ALLaM-AI Hugging Face org now redirects to humain-ai, so the weights resolve under HUMAIN's namespace; the model card still credits NCAI/SDAIA as the developer. The card claims MSA and English only.

TII's hybrid Transformer–Mamba series and its current open-weight flagship, released in sizes from 0.5B to 34B. Unlike Falcon 3, the model card lists Arabic among its 18 supported languages, making this the largest openly downloadable TII model with declared Arabic support.

Efficient open-weight model common in regional stacks; v0.3 is the current 7B instruct release and remains Apache 2.0. Arabic is not a declared language on the card. Note that Mistral's larger flagships moved to the non-open Mistral Research Licence, so the permissive terms apply to this size, not the family.

Open reasoning model under a plain MIT licence, allowing commercial use and derivatives including distillation. Arabic is not a declared target language — the card lists no languages — so Arabic behaviour is incidental. Superseded within the DeepSeek line by the R1-0528 update and later V3.x releases.

Open LLM family. The only model in this directory whose developer explicitly names a Saudi dialect: Qwen documents 119 languages and dialects including Arabic (Standard, Najdi, Levantine, Egyptian and others). Apache-2.0.

Meta's open-weight frontier family and a widely used base for regional Arabic fine-tunes. Arabic is one of the 12 languages Meta lists for Llama 4. The licence is a custom community licence with acceptable-use and above-700M-MAU conditions, not an OSI licence.

Arabic GPT-2 trained on the same corpus as AraBERTv2 and still a common Arabic generation baseline, published in base, medium, large and mega sizes. No licence is stated on the base model card.

Open-weight multilingual model covering 23 languages including Arabic. The licence is non-commercial (CC-BY-NC-4.0) plus Cohere's acceptable use addendum, so it cannot be used in commercial Arabic products.

Arabic-centric flagship of the Fanar 2.0 release (Mar 2026), continually pretrained from google/gemma-3-27b-pt on ~166B Arabic, English and code tokens with 32K context. It adds native Arabic reasoning traces, selective thinking mode and tool calling. This repo is text-in/text-out; image generation, image understanding and poetry are separate Fanar-2 models.

Qatar's sovereign Arabic LLM. This 8.7B instruct model — the 'Prime' branch — continually pretrains google/gemma-2-9b on 1T Arabic and English tokens; a separate 7B 'Star' model was trained from scratch. The card claims MSA plus Gulf, Levantine and Egyptian dialects, and alignment with Islamic values and Arab culture.

First Arabic model in the Falcon series (May 2025), built on Falcon3-7B by extending the tokenizer with 32,000 Arabic-specific tokens and training on non-translated Arabic data. TII kept it closed: no weights are published under tiiuae — only the evaluation detail datasets — and the model is reachable through chat.falconllm.tii.ae. The announcement claims MSA plus unnamed 'key dialects'.

Efficient open LLM series from Abu Dhabi's TII. The model card lists English, French, Spanish and Portuguese only — Arabic is not a supported language here, which is why TII built Falcon-Arabic by adding 32,000 Arabic tokens to this tokenizer. For Arabic from TII, use Falcon-H1 or Falcon-Arabic.

Successor to the Jais family, released as open weights in Aug 2026 in 8B and 70B chat sizes (plus GGUF builds). The card states it covers MSA, regional dialects and Arabic–English code-switching without naming the dialects. Repos are gated behind a contact-sharing agreement.

Landmark open Arabic LLM family (590M–70B), trained on Cerebras Condor Galaxy. The inceptionai org was renamed inception42, so the old repo URL only resolves via redirect; the repo is gated behind a contact-sharing agreement and has not been updated since Sept 2024. Superseded in practice by Jais 2.