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 / Cerebrium

Neocloud · USA

Cerebrium GPU pricing

10 GPUs priced today across 10 configurations. On average 7.5% above the market median.

Prices collected 2026-09-18 · seen since 2026-09-15

Jump to:Prices History Compare FAQ

Visit Cerebrium →

B200H200H100 SXMRTX PRO 6000 BlackwellA100 80GBA100 40GBL40SA10

Cerebrium'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

10of 10 ever seen

Cheapest anywhere for

0GPUs

Below market on

4of 10

Billing

On-demand

Every GPU Cerebrium prices, against the market

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

GPU	Cerebrium	Market	vs market	Per month	Sizes	Billing
NVIDIA B200	$6.01	$6.59	-9%	$4,329	1x · 1 config	on-demand
NVIDIA H200	$4.20	$4.45	-6%	$3,022	1x · 1 config	on-demand
NVIDIA H100 SXM	$3.40	$3.50	-3%	$2,447	1x · 1 config	on-demand
NVIDIA RTX PRO 6000 Blackwell	$2.50	$2.05	+22%	$1,799	1x · 1 config	on-demand
NVIDIA A100 80GB	$2.10	$1.79	+17%	$1,511	1x · 1 config	on-demand
NVIDIA A100 40GB	$2.00	$1.48	+35%	$1,439	1x · 1 config	on-demand
NVIDIA L40S	$1.95	$1.47	+33%	$1,405	1x · 1 config	on-demand
NVIDIA A10	$1.10	$1.29	-15%	$793	1x · 1 config	on-demand
NVIDIA L4	$0.80	$0.80	0%	$575	1x · 1 config	on-demand
NVIDIA T4	$0.59	$0.59	0%	$425	1x · 1 config	on-demand

Price history

Cerebrium has been in the index since 2026-09-15. 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. No price moved by more than 1% between consecutive snapshots so far.

Compare Cerebrium

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

Other neoclouds

RunPod Secure Cloud23 GPUs · +8.3% vs market Runcrate16 GPUs · +72.5% vs market Massed Compute12 GPUs · -3.6% vs market Modal11 GPUs · +13.5% vs market

Questions

How much does Cerebrium charge for an H100?

As of 2026-09-18, Cerebrium's on-demand H100 SXM works out to $3.40 per GPU-hour, 3% below the market median of $3.50. That is about $2,447 a month per GPU at 720 hours.

Is Cerebrium cheap?

Across the 10 GPUs it prices, Cerebrium averages 7.5% above the market median, and is cheaper than the median on 4 of them.

Where do these Cerebrium 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 Cerebrium actually published on those dates. Nothing is estimated or interpolated.

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

Open Cerebrium →