Skip to model comparison
AI Agent Store/Model comparisonsBuild an AI worker ↗

Inception / IFM · Download verified

Jais 3 MoVA-36B-A4B

Build an Arabic and English text assistant, including regional Arabic and Arabizi. Test it on the dialects, documents and tool workflows your users actually need.

Released 2026-10-15 · First reviewed 2026-10-25 · Checked 2026-11-03.

We still need comparable independent tests. You can compare the confirmed features and limits below, but we cannot yet give this version an Agent Fit or Practical Value rating. Try it on your hardware and tasks before relying on it.

Runs onYour hardwareHardware and setup costs apply
Documented capacity524KSee input limits below

What you can use today

You download the model files and supply the hardware and software to run them. Capacity is the amount of information a request can contain; settings and available memory can limit what fits.

Exact download ID: inception42/Jais-3-MoVA-36B-A4B. The provider recommends high thinking effort. Low is a research mode with reasoning disabled; the default is not confirmed. Your application executes any tools the model requests.

The publisher labels the downloadable files Apache 2.0. Use its matching K2-Horizon software and choose a model size that fits your hardware, leaving memory for the requests too.

The documented capacity is 524,288 tokens. Prompt, thinking and answer share this space; a maximum answer length is not established.

Budget for hardware, electricity and operation. No hosted token price or measured local running cost is confirmed.

Provider release and specifications ↗

Check availability and plans ↗

Provider documentation ↗

Test it before switching

Give each model the same examples, tools and definition of success. Record correct outcomes, response time, retries and total cost. Include the time and hardware needed to run it.

Compare caching and long-context costs ↗
AI Agent Store · Model comparisons · Data reviewed 2026-11-03Sources, limitations & corrections ↗