Aya Expanse 32B — VRAM, Speed & Local Setup

Written by Jakub Rusinowski · Last updated October 8, 2024

Model library → Aya Expanse → Aya Expanse 32B

The flagship multilingual model. State-of-the-art non-English performance across 23 languages. For enterprises and researchers needing robust global language support with a 128k context window.

Aya Expanse 32B needs about 20 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.

Specifications

Parameters32 Billion
Context window128,000
ArchitectureDense
ProviderCohere
LicenceCC-BY-NC
Specified atQ4_K_M
System RAM32 GB
Record updated2024-10-08

Licence

CC-BY-NC-4.0 — research / non-commercial only. Research / non-commercial only — this licence does NOT permit shipping a commercial product.

VRAM and Speed by Quantization

Modelled on a reference NVIDIA RTX 4090 (24 GB), at 8K context. Speed figures are ESTIMATES from the memory-bandwidth roofline described on the methodology page, not benchmarks we ran — rows marked measured come from published or reader-submitted runs. VRAM here includes the KV cache, so it reads higher than the headline figure above, which does not.

QuantWeightsVRAM neededEst. speedFit on 24 GB
Q2_K10.6 GB12.8 GB~58 tok/s (est.)Fits comfortably
Q3_K_M13.8 GB15.9 GB~47 tok/s (est.)Fits comfortably
Q4_K_M19.5 GB21.6 GB~35 tok/s (est.)Tight fit
Q5_K_M22.9 GB25.0 GB~4 tok/s (est.)Offloads to system RAM (slow)
Q6_K26.5 GB28.6 GB~4 tok/s (est.)Offloads to system RAM (slow)
Q8_034.3 GB36.5 GB~3 tok/s (est.)Offloads to system RAM (slow)
F1664.6 GB66.7 GB—Won't fit

Want the memory numbers alone, at every quantization level and your own context length? Use the Aya Expanse 32B VRAM calculator.

Buy This HardwareAMD Radeon RX 7900 XTX 24GB — 24 GB VRAM · 355 W board powerDeploy in the Cloud NowRTX 4090 on RunPod — from $0.34/hr · rate checked 2026-07

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.

Recommended GPU

The cheapest catalogued GPU that runs Aya Expanse 32B is the AMD Radeon RX 7900 XT (20 GB).

Affiliate disclosure: Some links on this page are affiliate links — if you buy through them, LLM Configurator may earn a commission at no extra cost to you. As an Amazon Associate, LLM Configurator earns from qualifying purchases.
AMD Radeon RX 7900 XT 20GB
20 GB VRAM · 315 W board power
2026 prices are volatile — check the current listing.
Check price on Amazon

How to Run Aya Expanse 32B

Install Ollama, then run:

ollama run aya-expanse:32b

Weights on Hugging Face: CohereForAI/aya-expanse-32b.

Best for: multilingual, enterprise, translation, global chat.

Can I Run Aya Expanse 32B on My GPU?

Other Aya Expanse Sizes

Aya Expanse 32B — Frequently Asked Questions

How much VRAM does Aya Expanse 32B need?
About 20 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 Expanse 32B run on an RTX 4090 (24 GB)?
Yes. Aya Expanse 32B needs about 20 GB at Q4_K_M, inside a 24 GB card, at an estimated 35 tokens/sec.
How do I run Aya Expanse 32B locally?
Install Ollama and run `ollama run aya-expanse:32b`. That pulls the weights and starts a local OpenAI-compatible endpoint; after the download nothing leaves the machine.
What other sizes does Aya Expanse come in?
Aya Expanse 8B (6 GB), Aya Expanse 32B (20 GB). Every size shares the family's training and licence; the larger ones score higher and need proportionally more memory.

← All Aya Expanse models | VRAM calculator | Build a PC for this model | Check your own hardware