Aya 3B — VRAM, speed & local setup
Written by Jakub Rusinowski · Last updated
Best 3B multilingual model available. Supports 23+ languages with SOTA quality. Ideal for phones, Raspberry Pi, and offline multilingual assistants. Requires just 2–3 GB VRAM.
Aya 3B needs about 3 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). Weights plus overhead only: this model's architecture is unpublished, so no KV cache is added.
| Quant | Memory | VRAM | Speed (est.) | Fit |
|---|---|---|---|---|
| Q2_K 2.63 bpw | 1.8 GB | ~244 tok/s | Fits | |
| Q3_K_M 3.41 bpw | 2.1 GB | ~223 tok/s | Fits | |
| Q4_K_M 4.83 bpw | 2.6 GB | ~192 tok/s | Fits | |
| Q5_K_M 5.67 bpw | 2.9 GB | ~178 tok/s | Fits | |
| Q6_K 6.56 bpw | 3.3 GB | ~165 tok/s | Fits | |
| Q8_0 8.50 bpw | 4 GB | ~143 tok/s | Fits | |
| F16 16.00 bpw | 6.8 GB | ~93 tok/s | Fits |
Black marker = usable memory on the NVIDIA RTX 4090 (24 GB). Estimates from the memory-bandwidth roofline on the methodology page. Aya 3B VRAM calculator →
Get Aya 3B running
The cheapest catalogued GPU that runs Aya 3B is the Intel Arc B570 (10 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 Aya 3B
Install Ollama, then run:
ollama run aya:3bSpecifications
Preview — The model is released, but these specs are thin or rest on a single source. Individual fields may be wrong.
Preview — The model is released, but these specs are thin or rest on a single source. Individual fields may be wrong.
- Parameters
- 3 Billion
- Context window
- 8,192
- Architecture
- Dense
- Provider
- Cohere
- Licence
- CC-BY-NC 4.0
- Practical deployment
- Edge device (phone, SBC)
- Specified at
- Q4_K_M
- System RAM
- 8 GB
- Record updated
- 2026-02-17
Research / non-commercial only — this licence does NOT permit shipping a commercial product.
Quality and use cases
Scores as published by the model’s authors or an independent evaluator — quality, not throughput, and not measured by us.
Can I run Aya 3B on my GPU?
Aya 3B — frequently asked questions
How much VRAM does Aya 3B need?
About 3 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 Aya 3B run on an RTX 4090 (24 GB)?
Yes. Aya 3B needs about 3 GB at Q4_K_M, inside a 24 GB card, at an estimated 192 tokens/sec.
How do I run Aya 3B locally?
Install Ollama and run `ollama run aya:3b`. That pulls the weights and starts a local OpenAI-compatible endpoint; after the download nothing leaves the machine.