What GPU do I need to run CohereLabs/aya-expanse-8b?

8.0B parameters, published in F16. View on Hugging FaceGated

8.0B
Parameters
F16
Native precision
CohereForCausalLM
Architecture
text-generation
Pipeline

aya-expanse-8b is published by CohereLabs on Hugging Face, with 16,800 downloads and 445 likes to date. It's a CohereForCausalLM model built for text-generation, published natively in F16, and gated: you'll need to accept the model's terms on Hugging Face before downloading weights.

VRAM required & cheapest live GPU fit

Required VRAM = weight size at each precision times a flat 1.2 overhead for activations and fragmentation. The KV-cache grows with context and is not in that factor; it is listed per model below where the architecture is published. Full formula and assumptions: methodology.

PrecisionWeight sizeRequired VRAMCheapest live fitGPUs neededEst. $/hr (full fit)
FP1615.0 GB17.9 GBRTX A50001$0.176/hr
FP8 (quantized)7.5 GB9.0 GBRTX 5060 Ti1$0.165/hr
INT4 (quantized)3.7 GB4.5 GBRTX 30701$0.088/hr

A GPU is only matched to a row if its hardware supports that precision, and the primary recommendation is always a single-GPU fit when one exists.

INT4 requires a quantized checkpoint actually published for this model, check its Hugging Face page before relying on this row.

Cheapest way to run aya-expanse-8b at its published (F16) precision: 1× RTX A5000, at $0.176/hr per GPU ($0.176/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.

aya-expanse-8b: KV cache by context length

The KV cache is the memory the attention layers hold for every token of context, on top of the weights. It is not part of the flat 1.2x overhead in the table above, grows with context length and with every concurrent request, and is why a long-context deployment needs more VRAM than the table shows.

KV-cache size for aya-expanse-8b is not published for this architecture, so no figure is shown.

aya-expanse-8b: common questions

Does aya-expanse-8b fit on a 24 GB GPU?

Yes. At FP16 it needs 17.9 GB of VRAM, so a 24 GB card holds it with 6.1 GB to spare. A 16 GB card is not enough for it at FP16.

Do I need approval to download aya-expanse-8b?

Yes. CohereLabs gates this repository on Hugging Face, so you have to accept its terms with a signed-in account before the weights will download. It does not change the 17.9 GB the model needs once you have them.

What is the least VRAM aya-expanse-8b can run in?

4.5 GB, at INT4 (quantized), which fits a 6 GB card, against 17.9 GB at FP16. That row assumes an INT4 checkpoint has actually been published for this model, so check its Hugging Face page before planning around it.

Does quantizing aya-expanse-8b lower the GPU bill?

Yes. At FP16 the cheapest live fit is one RTX A5000 at $0.176/hr. At INT4 (quantized) it drops to one RTX 3070 at $0.088/hr, provided a quantized checkpoint exists for it.

Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.

Aya models

Alternatives at this size

Other models for text-generation within about a third of aya-expanse-8b's 8.0B parameters, from other model lines.

More on aya-expanse-8b

Related reading: RTX A5000 pricing and specs, How much VRAM you need for LLMs, Serving LLMs with vLLM, vLLM vs TensorRT-LLM vs SGLang, and Best GPU for LLM inference.

Your own GPU cloud accounts

One console for the GPU clouds you already rent from. Your keys stay on your machine.

$20 a month, flat

Connect your accounts

One console for the GPU clouds you already use.

Connect your accounts for $20 a month, flat. Your provider bills the GPU.

© 2026 Aquanode. All rights reserved.

All trademarks, logos and brand names are the property of their respective owners.