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 / Providers / Spheron

Marketplace

Spheron GPU pricing

12 GPUs priced today across 14 configurations. On average 5.4% above the market median.

Prices collected 2026-09-18 · seen since 2026-09-11

Jump to:Prices History Changes Compare FAQ

Visit Spheron →

B300B200H200MI300XGH200H100 SXMRTX PRO 6000 BlackwellA100 80GB

Spheron's on-demand median per GPU-hour, per snapshot — its eight most expensive GPUs. Gaps are runs where the GPU was not listed.

At a glance

GPUs priced

12of 12 ever seen

Cheapest anywhere for

0GPUs

Below market on

5of 12

Billing

On-demand

Every GPU Spheron prices, against the market

Per GPU-hour, on-demand, 2026-09-18. vs market compares Spheron's own median for that GPU with the index median across every provider. Click a GPU for every provider's price.

GPU	Spheron	Market	vs market	Per month	Sizes	Billing
NVIDIA B300	$10.21	$7.85	+30%	$7,351	1x · 1 config	on-demand
NVIDIA B200	$9.36	$6.59	+42%	$6,739	1x · 1 config	on-demand
NVIDIA H200	$4.79	$4.45	+8%	$3,449	1x · 1 config	on-demand
AMD MI300X	$3.59	$2.59	+39%	$2,585	1x · 1 config	on-demand
NVIDIA GH200	$3.02	$3.02	0%	$2,174	1x · 1 config	on-demand
NVIDIA H100 SXM	$2.64	$3.50	-24%	$1,901	1x · 3 configs	on-demand
NVIDIA RTX PRO 6000 Blackwell	$2.27	$2.05	+11%	$1,634	1x · 1 config	on-demand
NVIDIA A100 80GB	$1.43	$1.79	-20%	$1,030	1x · 1 config	on-demand
NVIDIA L40S	$0.96	$1.47	-35%	$691	1x · 1 config	on-demand
NVIDIA RTX 6000 Ada	$0.78	$0.82	-4%	$562	1x · 1 config	on-demand
NVIDIA RTX 4090	$0.72	$0.60	+20%	$518	1x · 1 config	on-demand
NVIDIA RTX 5090	$0.68	$0.69	-1%	$490	1x · 1 config	on-demand

Price history

Spheron has been in the index since 2026-09-11. The chart at the top draws its on-demand median per GPU on every snapshot; a gap is a run where the GPU was not listed, never a guess.

Recent price changes

When	GPU	From	To	Change
2026-09-18 22:13	NVIDIA RTX 4090	$0.58	$0.72	+24.1%
2026-09-18 22:13	NVIDIA B300	$9.62	$10.21	+6.1%
2026-09-18 22:13	NVIDIA A100 80GB	$1.48	$1.43	-3.4%
2026-09-18 22:13	NVIDIA RTX PRO 6000 Blackwell	$2.31	$2.27	-1.7%
2026-09-18 20:56	NVIDIA RTX 5090	$0.84	$0.68	-19%
2026-09-18 20:56	NVIDIA GH200	$2.75	$3.02	+9.8%
2026-09-18 20:56	NVIDIA A100 80GB	$1.43	$1.48	+3.5%
2026-09-18 20:56	NVIDIA RTX PRO 6000 Blackwell	$2.27	$2.31	+1.8%
2026-09-18 16:27	NVIDIA H200	$5.92	$4.80	-18.9%
2026-09-18 16:27	NVIDIA H100 SXM	$2.33	$2.64	+13.5%
2026-09-18 16:27	NVIDIA GH200	$3.02	$2.75	-8.9%
2026-09-18 16:27	NVIDIA RTX PRO 6000 Blackwell	$2.35	$2.27	-3.4%

A change is the provider's median for that GPU moving between two consecutive snapshots. Listings appearing or disappearing are not counted.

Compare Spheron

Spheron vs RunPod Community CloudSame GPUs, both prices, who is cheaper on each Spheron vs RunPod Secure CloudSame GPUs, both prices, who is cheaper on each Spheron vs Vast.aiSame GPUs, both prices, who is cheaper on each Spheron vs GPU.aiSame GPUs, both prices, who is cheaper on each Spheron vs io.netSame GPUs, both prices, who is cheaper on each Spheron vs RuncrateSame GPUs, both prices, who is cheaper on each

Other marketplaces

RunPod Community Cloud25 GPUs · -30.8% vs market Vast.ai23 GPUs · +0.1% vs market GPU.ai21 GPUs · -9.5% vs market io.net21 GPUs · -7.1% vs market

Questions

How much does Spheron charge for an H100?

As of 2026-09-18, Spheron's on-demand H100 SXM works out to $2.64 per GPU-hour, 24% below the market median of $3.50. That is about $1,901 a month per GPU at 720 hours.

Is Spheron cheap?

Across the 12 GPUs it prices, Spheron averages 5.4% above the market median, and is cheaper than the median on 5 of them. As a marketplace its listings are independent hosts, so the price is a spread and the cheapest listing may be a single machine.

Where do these Spheron prices come from?

Public pricing page, parsed. Per-GPU price is the listed per-GPU rate, or the node price divided by GPU count. Prices near reserved, committed or contract terms are discarded; anything outside a plausible range for the GPU is discarded. Prices are collected every six hours and every snapshot is kept, so the history above is what Spheron actually published on those dates. Nothing is estimated or interpolated.

Does Spheron offer spot or reserved pricing?

No spot or interruptible rates were listed on the pricing we read. Reserved pricing, where it exists, is by quote and not published. Only on-demand prices enter the index median.

Rent from Spheron? The link goes to their site; the prices above are theirs, read from their public pricing.

Open Spheron →