Jais 3 32B — VRAM, speed & local setup
Written by Jakub Rusinowski · Last updated
The large dense Jais 3: 32B-class (34.8B in the files), Arabic and English, a 512K-token context and reasoning-effort control. Apache-2.0; official GGUF (Q4_K_M 21.1 GB), FP8 and MLX builds.
Jais 3 32B needs about 22 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache. On Apple Silicon that figure comes out of unified memory.
VRAM and speed by quantization
Quoted against NVIDIA RTX 4090 (24 GB). Includes the KV cache at 8K context, so it reads higher than the headline figure.
| Quant | Memory | VRAM | Speed (est.) | Fit |
|---|---|---|---|---|
| Q2_K 2.63 bpw | 14.4 GB | ~53 tok/s | Fits | |
| Q3_K_M 3.41 bpw | 17.8 GB | ~43 tok/s | Fits | |
| Q4_K_M 4.83 bpw | 24 GB | ~5 tok/s | Offload | |
| Q5_K_M 5.67 bpw | 27.6 GB | ~4 tok/s | Offload | |
| Q6_K 6.56 bpw | 31.5 GB | ~4 tok/s | Offload | |
| Q8_0 8.50 bpw | 39.9 GB | ~3 tok/s | Offload | |
| F16 16.00 bpw | 72.5 GB | — | Too big |
Black marker = usable memory on the NVIDIA RTX 4090 (24 GB). Estimates from the memory-bandwidth roofline on the methodology page. Jais 3 32B VRAM calculator →
Get Jais 3 32B running
The cheapest catalogued GPU that runs Jais 3 32B is the NVIDIA GeForce RTX 5090 (32 GB).
or compare on Vast.ai from $0.35/hr (typical low · varies)
As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.
How to run Jais 3 32B
Install Ollama, then run:
ollama run jais-3Specifications
Verified — Checked against the primary source — the model card or the vendor spec page — and corroborated by a second independent source.
- Parameters
- 32 Billion (34.8B in the files)
- Context window
- 524,288
- Architecture
- Dense transformer (K2 Horizon, GQA)
- Provider
- Inception / MBZUAI Institute of Foundation Models
- Licence
- Apache-2.0
- Availability
- Weights downloadable
- Practical deployment
- Single consumer GPU
- Specified at
- Q4_K_M
- System RAM
- 32 GB
- Record updated
- 2026-11-11
Commercial use permitted. No usage restrictions beyond attribution.
See also Jais 3 7B
Quality and use cases
Scores as published by the model’s authors or an independent evaluator — quality, not throughput, and not measured by us.
Other Jais 3 sizes
Jais 3 32B — frequently asked questions
How much VRAM does Jais 3 32B need?
About 22 GB at Q4_K_M — quantized weights plus framework overhead, before any KV cache. The cache grows with context length and is added on top; the table above folds it in. Apple Silicon counts unified memory toward the same figure.
Does Jais 3 32B run on an RTX 4090 (24 GB)?
Yes. Jais 3 32B needs about 22 GB at Q4_K_M, inside a 24 GB card, at an estimated 5 tokens/sec.
How do I run Jais 3 32B locally?
Install Ollama and run `ollama run jais-3`. That pulls the weights and starts a local OpenAI-compatible endpoint; after the download nothing leaves the machine.
What other sizes does Jais 3 come in?
Jais 3 7B (6 GB), Jais 3 32B (22 GB), Jais 3 375B-A23B (230 GB). Every size shares the family's training and licence; the larger ones score higher and need proportionally more memory.