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 / Sri Lanka

🇱🇰 Asia · LKR

GPU rental prices in Sri Lanka

No provider we track is headquartered or hosts machines in Sri Lanka today — every one of them sells here, so this page prices the whole market in LKR and lists the nearest providers on the Asia continent. Converted at Rs331/$ (2026-10-11). The global H100 median is Rs1,157.51/hr.

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

Every GPU, priced in LKR

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

GPU	Median Rs/hr	Cheapest	at	Rs / month	Providers
NVIDIA H100 SXM	Rs1,157.51	Rs555.60	Latitude.sh	Rs833,405	43
NVIDIA A100 80GB	Rs591.98	Rs123.96	Vast.ai	Rs426,227	35
NVIDIA H200	Rs1,488.22	Rs661.43	io.net	Rs1,071,521	31
NVIDIA L40S	Rs426.62	Rs177.12	Vast.ai	Rs307,169	27
NVIDIA B200	Rs2,311.71	Rs1,240.19	Packet.ai	Rs1,664,429	25
NVIDIA RTX PRO 6000 Blackwell	Rs735.84	Rs264.57	HyperAI	Rs529,808	24
NVIDIA L4	Rs262.79	Rs88.93	Vast.ai	Rs189,207	18
NVIDIA B300	Rs2,645.73	Rs1,488.22	io.net	Rs1,904,926	17
NVIDIA RTX A6000	Rs191.82	Rs109.14	RunPod Community Cloud	Rs138,107	16
NVIDIA A100 40GB	Rs601.90	Rs261.27	io.net	Rs433,371	15
NVIDIA V100 16GB	Rs256.31	Rs39.87	Vast.ai	Rs184,540	13
NVIDIA RTX 4090	Rs158.74	Rs99.21	io.net	Rs114,296	13
NVIDIA RTX 6000 Ada	Rs294.34	Rs163.29	Vast.ai	Rs211,923	10
NVIDIA L40	Rs289.38	Rs218.27	io.net	Rs208,351	10
NVIDIA RTX 5090	Rs266.23	Rs146.50	Vast.ai	Rs191,683	10
NVIDIA H100 PCIe	Rs756.25	Rs525.84	io.net	Rs544,499	8
NVIDIA T4	Rs195.25	Rs52.91	Akash	Rs140,584	8
NVIDIA RTX A5000	Rs84.33	Rs52.91	RunPod Community Cloud	Rs60,720	8
NVIDIA RTX A4000	Rs52.91	Rs25.77	Vast.ai	Rs38,099	8
NVIDIA A10	Rs426.62	Rs330.72	OVHcloud	Rs307,169	7
NVIDIA A40	Rs195.12	Rs115.75	RunPod Community Cloud	Rs140,488	7
NVIDIA RTX 3090	Rs72.76	Rs45.69	Vast.ai	Rs52,385	7
AMD MI300X	Rs998.76	Rs165.36	RunPod Community Cloud	Rs719,110	6
NVIDIA H100 NVL	Rs926.83	Rs681.28	GPU.ai	Rs667,319	6
NVIDIA RTX 4080	Rs89.09	Rs49.61	Akash	Rs64,148	6
NVIDIA H200 NVL	Rs1,253.41	Rs165.36	RunPod Community Cloud	Rs902,459	5
NVIDIA RTX 5080	Rs124.85	Rs72.15	Vast.ai	Rs89,889	5
NVIDIA GH200	Rs1,139.32	Rs757.34	Lambda	Rs820,309	4
NVIDIA V100 32GB	Rs958.09	Rs519.22	io.net	Rs689,821	4
NVIDIA A10G	Rs502.23	Rs332.70	Amazon Web Services	Rs361,603	2
AMD MI355X	Rs2,844.16	Rs2,844.16	Oracle Cloud	Rs2,047,795	1
AMD MI325X	Rs1,256.72	Rs1,256.72	DigitalOcean GPU Droplets	Rs904,840	1

Nearest providers by headquarters — Asia

GPU.aiUAE · 22 GPUs · -12.1% vs market E2E NetworksIndia · 8 GPUs · +9.2% vs market JarvislabsIndia · 6 GPUs · -18.7% vs market Cyfuture AIIndia · 3 GPUs · +3.3% vs market HyperAIChina · 2 GPUs · -56.3% vs market NeysaIndia · 2 GPUs · +28% vs market

Questions

How much does it cost to rent an H100 in Sri Lanka?

Across every provider we track, the global median is $3.50 (Rs1,157.51) and the cheapest listing anywhere is $1.68 at Latitude.sh — any of them will sell to a customer in Sri Lanka.

Are there GPU cloud providers in Sri Lanka?

None of the 45 providers we track is headquartered in Sri Lanka. The nearest by headquarters are on the same continent: GPU.ai, E2E Networks, Jarvislabs, Cyfuture AI, HyperAI. Every provider in the index sells worldwide; the question is latency, data residency and invoicing, not availability.

What does the LKR price mean?

Providers publish in dollars (a few in euros). This page converts at the rate captured with the snapshot — Rs331 per dollar on 2026-10-11 — so every GPU sits on one axis in LKR. 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 LKR figure as a comparison, not an invoice.

Which GPU is the best value from Sri Lanka?

For holding a model, memory per LKR: the NVIDIA RTX 3090 gives 109.1 GB per Rs1 (at Rs72.76/hr). The cheapest GPU-hour of any kind is the NVIDIA RTX A4000 at Rs52.91. The full table above prices every GPU we track in LKR; 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 Sri Lanka, where any exist, which is what matters for latency and data residency.

Elsewhere in Asia

🇮🇳 India 🇨🇳 China 🇰🇷 South Korea 🇹🇼 Taiwan 🇯🇵 Japan 🇹🇭 Thailand 🇶🇦 Qatar 🇹🇷 Türkiye 🇮🇩 Indonesia 🇳🇵 Nepal 🇴🇲 Oman 🇦🇪 United Arab Emirates

Every country, and every provider worldwide against the market.

All countries →