Autor: Jakub Rusinowski · Ostatnia aktualizacja: 17 lutego 2026
Wydanie Cohere z 17 lutego 2026 — najpotężniejszy wielojęzykowy model open-weight klasy 3B. Tiny Aya przewyższa Qwen3-4B, Gemma 3 4B i Ministral 3B w benchmarkach wielojęzykowych w 23 językach. Idealny dla urządzeń edge, telefonów i wdrożeń z ograniczonymi zasobami.
| Licence | What it permits | Applies to |
|---|---|---|
CC-BY-NC-4.0 | Research / non-commercial only Research / non-commercial only — this licence does NOT permit shipping a commercial product. | Aya 3B |
| Aya 3B | Min 3 GB VRAM · Q4_K_M · 8,192 ctx · ollama run aya:3b |
The cheapest GPU that runs Aya 3B (Tiny Aya) locally (min 3 GB VRAM) is the Intel Arc B570 (10 GB).
Install Ollama then run: ollama run aya:3b
Minimum VRAM: 3 GB. For best results use Q4_K_M quantization.
Aya 3B (Tiny Aya) needs about 3 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: Aya 3B (3 GB, Q4_K_M). On Apple Silicon, unified memory counts toward this requirement.
Yes — Aya 3B (Tiny Aya) 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.
Q4_K_M is the best balance of quality and VRAM for Aya 3B (Tiny Aya) 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.
Install Ollama, then run: ollama run aya:3b. This downloads Aya 3B (Tiny Aya) and starts a local, OpenAI-compatible endpoint — no internet connection is needed after the initial download.