IFM and Inception42 Launch Jais 3 Arabic AI Models

Oct 15, 2026
Jais 3 includes six open language models and an Arabic speech recognition model, with support for regional dialects, tool use, and a 512,000 token context window.

Institute of Foundation Models (IFM) and Inception42 introduced Jais 3 in a press release, a fleet of six open language models and an Arabic speech recognition model. The language models range from 900 million to 375 billion parameters and are based on IFM's K2 Horizon models.

Jais 3 supports Modern Standard Arabic and regional dialects from the Gulf to North Africa. It can process speech that switches between Arabic, English, and French, while Jais Speech can identify dialects, retain foreign words in their original script, and add Arabic vowel marks to transcripts.

The language models share a 512,000 token context window and support tool use for tasks involving documents, spreadsheets, presentations, websites, and web searches. In evaluations conducted by IFM and Inception42, the 3.7 billion parameter model outperformed the open models tested with up to 5 billion parameters on Arabic and agent tasks.

Jais 3 and Jais Speech are available on Hugging Face, with deployment support for vLLM and SGLang. IFM is also releasing its audited Arabic benchmarks, evaluation code, and five training checkpoints for each model.

We hope you enjoyed this article

Consider subscribing to one of our newsletters like Daily AI Brief.

Also, consider following us on social media:

Free newsletter

Daily AI Brief

Daily report covering major AI developments and industry news, with both top stories and complete market updates

Whitepaper

Tensordyne Napier: What If One Rack Could Do the Work of Nine?

Tensordyne

This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.

Read more

You may also like

Free, six days a week

Daily AI Brief: the AI news that matters, in your inbox.