Jais 3 — local AI model by Inception / MBZUAI Institute of Foundation Models
Written by Jakub Rusinowski · Last updated
Jais 3 is an Arabic-English model family from Inception and MBZUAI's Institute of Foundation Models, built on the K2 Horizon architecture: dense 0.9B to 32B models and a 375B mixture-of-experts, all with a 512K-token context and Apache-2.0. Official GGUF and MLX builds cover the dense models.
Variants
The smallest Jais 3 variant needs about 6 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache.
| Model | VRAM at Q4 | VRAM | Context | Run it |
|---|---|---|---|---|
| Jais 3 7B → 7B | ~6.4 GB | 524,288 | ollama run jais-3 | |
| Jais 3 32B → 32B | ~21.9 GB | 524,288 | ollama run jais-3 | |
| Jais 3 375B-A23B → 375B (23B active) | ~229.7 GB | 524,288 | ollama run jais-3 |
Memory is quantized weights plus overhead at Q4_K_M, from the same engine as the GPU & VRAM checker.
How to run Jais 3 locally
Install Ollama, then pull the tag.
ollama run jais-3Pick a size above for its own VRAM figure, speed estimate and install command.
Licence
Commercial use permitted. No usage restrictions beyond attribution.
Applies to: Jais 3 7B, Jais 3 32B, Jais 3 375B-A23BRecommended GPU
The cheapest catalogued GPU that runs Jais 3 locally (min 6 GB VRAM) is the Intel Arc B570 (10 GB).
Jais 3 — frequently asked questions
How much VRAM does Jais 3 need?
Jais 3 needs about 6 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: Jais 3 7B (6 GB, Q4_K_M); Jais 3 32B (22 GB, Q4_K_M); Jais 3 375B-A23B (230 GB, Q4_K_M). On Apple Silicon, unified memory counts toward this requirement.
Can I run Jais 3 on an RTX 4090 (24 GB)?
Yes — Jais 3 runs on an RTX 4090 (24 GB) and other 24 GB cards such as the RTX 3090. Smaller variants also fit comfortably on 8–16 GB GPUs at Q4_K_M.
What quantization should I use for Jais 3?
Q4_K_M is the best balance of quality and VRAM for Jais 3 in most cases. Choose Q8_0 for near-lossless quality if you have spare VRAM, or smaller quants (Q3/Q2) only when memory is tight.
How do I run Jais 3 with Ollama?
Jais 3 has no local Ollama tag — the published tag is cloud-hosted, so running it sends your prompts to a hosted GPU rather than your own machine.