Runyard is a free hardware-aware AI model browser. You enter your CPU, GPU, and VRAM and it instantly shows every local LLM that will run on your machine, ranked by speed and quality.

How much VRAM do I need to run local LLMs?

8GB of VRAM runs 7B models like Llama 3.1 8B and Mistral 7B at Q4 quantization. 16GB unlocks 13B models. 24GB lets you run Mixtral 8x7B and Llama 3 70B at lower quantization.

What is the best local LLM for my GPU?

Use Runyard at www.runyard.dev — enter your GPU and VRAM and the Model Radar will rank every compatible LLM for your exact hardware, showing estimated tokens per second for each model.

Can I run Llama 3 locally?

Yes. Llama 3.1 8B at Q4 runs on any 8GB VRAM GPU. Llama 3.1 70B needs around 40GB VRAM at Q4, or an Apple Silicon Mac with 64GB+ unified memory.

RRunyard Index

Runyard / GPU Index / Countries / Peru

🇵🇪 South America · PEN

GPU rental prices in Peru

No provider we track is headquartered or hosts machines in Peru today — every one of them sells here, so this page prices the whole market in PEN and lists the nearest providers on the America continent. Converted at PEN 3.44/$ (2026-10-11). The global H100 median is PEN 12.05/hr.

Prices collected 2026-10-11 · every figure is a provider's own published rate

Every GPU, priced in PEN

The whole index — 32 GPUs from every provider we track, each of which will rent to a customer in Peru — with the global median and the single cheapest listing converted to PEN at the snapshot's rate. Tax is not included.

GPU	Median PEN/hr	Cheapest	at	PEN / month	Providers
NVIDIA H100 SXM	PEN 12.05	PEN 5.78	Latitude.sh	PEN 8,674	43
NVIDIA A100 80GB	PEN 6.16	PEN 1.29	Vast.ai	PEN 4,436	35
NVIDIA H200	PEN 15.49	PEN 6.88	io.net	PEN 11,153	31
NVIDIA L40S	PEN 4.44	PEN 1.84	Vast.ai	PEN 3,197	27
NVIDIA B200	PEN 24.06	PEN 12.91	Packet.ai	PEN 17,324	25
NVIDIA RTX PRO 6000 Blackwell	PEN 7.66	PEN 2.75	HyperAI	PEN 5,514	24
NVIDIA L4	PEN 2.74	PEN 0.93	Vast.ai	PEN 1,969	18
NVIDIA B300	PEN 27.54	PEN 15.49	io.net	PEN 19,827	17
NVIDIA RTX A6000	PEN 2.00	PEN 1.14	RunPod Community Cloud	PEN 1,437	16
NVIDIA A100 40GB	PEN 6.26	PEN 2.72	io.net	PEN 4,511	15
NVIDIA V100 16GB	PEN 2.67	PEN 0.41	Vast.ai	PEN 1,921	13
NVIDIA RTX 4090	PEN 1.65	PEN 1.03	io.net	PEN 1,190	13
NVIDIA RTX 6000 Ada	PEN 3.06	PEN 1.70	Vast.ai	PEN 2,206	10
NVIDIA L40	PEN 3.01	PEN 2.27	io.net	PEN 2,169	10
NVIDIA RTX 5090	PEN 2.77	PEN 1.52	Vast.ai	PEN 1,995	10
NVIDIA H100 PCIe	PEN 7.87	PEN 5.47	io.net	PEN 5,667	8
NVIDIA T4	PEN 2.03	PEN 0.55	Akash	PEN 1,463	8
NVIDIA RTX A5000	PEN 0.88	PEN 0.55	RunPod Community Cloud	PEN 632	8
NVIDIA RTX A4000	PEN 0.55	PEN 0.27	Vast.ai	PEN 397	8
NVIDIA A10	PEN 4.44	PEN 3.44	OVHcloud	PEN 3,197	7
NVIDIA A40	PEN 2.03	PEN 1.20	RunPod Community Cloud	PEN 1,462	7
NVIDIA RTX 3090	PEN 0.76	PEN 0.48	Vast.ai	PEN 545	7
AMD MI300X	PEN 10.40	PEN 1.72	RunPod Community Cloud	PEN 7,485	6
NVIDIA H100 NVL	PEN 9.65	PEN 7.09	GPU.ai	PEN 6,946	6
NVIDIA RTX 4080	PEN 0.93	PEN 0.52	Akash	PEN 668	6
NVIDIA H200 NVL	PEN 13.05	PEN 1.72	RunPod Community Cloud	PEN 9,393	5
NVIDIA RTX 5080	PEN 1.30	PEN 0.75	Vast.ai	PEN 936	5
NVIDIA GH200	PEN 11.86	PEN 7.88	Lambda	PEN 8,538	4
NVIDIA V100 32GB	PEN 9.97	PEN 5.40	io.net	PEN 7,180	4
NVIDIA A10G	PEN 5.23	PEN 3.46	Amazon Web Services	PEN 3,764	2
AMD MI355X	PEN 29.60	PEN 29.60	Oracle Cloud	PEN 21,314	1
AMD MI325X	PEN 13.08	PEN 13.08	DigitalOcean GPU Droplets	PEN 9,418	1

Nearest providers by headquarters — South America

Latitude.shBrazil · 3 GPUs · -5.7% vs market

Questions

How much does it cost to rent an H100 in Peru?

Across every provider we track, the global median is $3.50 (PEN 12.05) and the cheapest listing anywhere is $1.68 at Latitude.sh — any of them will sell to a customer in Peru.

Are there GPU cloud providers in Peru?

None of the 45 providers we track is headquartered in Peru. The nearest by headquarters are on the same continent: Latitude.sh. Every provider in the index sells worldwide; the question is latency, data residency and invoicing, not availability.

What does the PEN price mean?

Providers publish in dollars (a few in euros). This page converts at the rate captured with the snapshot — PEN 3.44 per dollar on 2026-10-11 — so every GPU sits on one axis in PEN. Your card will be charged in the provider's billing currency at your bank's rate, and local tax is added on top, so treat the PEN figure as a comparison, not an invoice.

Which GPU is the best value from Peru?

For holding a model, memory per PEN: the NVIDIA RTX 3090 gives 109.1 GB per PEN 1 (at PEN 0.76/hr). The cheapest GPU-hour of any kind is the NVIDIA RTX A4000 at PEN 0.55. The full table above prices every GPU we track in PEN; the cheapest-listing column links to who sells it.

Is the price the same everywhere in the world?

Nearly. Most providers publish one price list regardless of where you are, so the market table on this page is the same market a buyer in any country sees — the differences are tax, currency and, for the hyperscalers, region. What does change by country is who has hardware nearby: the hosted-hardware section lists machines actually located in Peru, where any exist, which is what matters for latency and data residency.

Elsewhere in South America

🇧🇷 Brazil 🇦🇷 Argentina 🇨🇱 Chile

Every country, and every provider worldwide against the market.

All countries →