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 / Massed Compute

Neocloud · USA

Massed Compute GPU pricing

12 GPUs priced today across 18 configurations. On average 3.6% below the market median.

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

Jump to:Prices History Compare FAQ

Visit Massed Compute →

B300B200H200 NVLH100 NVLH100 SXMRTX PRO 6000 BlackwellA100 80GBL40S

Massed Compute'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

7of 12

Billing

On-demand

Every GPU Massed Compute prices, against the market

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

GPU	Massed Compute	Market	vs market	Per month	Sizes	Billing
NVIDIA B300	$6.60	$7.85	-16%	$4,752	8x · 1 config	on-demand
NVIDIA B200	$5.43	$6.59	-18%	$3,911	8x · 1 config	on-demand
NVIDIA H200 NVL	$3.72	$3.72	0%	$2,678	1x–4x · 2 configs	on-demand
NVIDIA H100 NVL	$3.02	$3.03	-1%	$2,171	1x–2x · 2 configs	on-demand
NVIDIA H100 SXM	$2.81	$3.50	-20%	$2,023	1x · 2 configs	on-demand
NVIDIA RTX PRO 6000 Blackwell	$2.19	$2.05	+7%	$1,577	1x · 1 config	on-demand
NVIDIA A100 80GB	$1.37	$1.79	-24%	$983	1x · 2 configs	on-demand
NVIDIA L40S	$0.97	$1.47	-34%	$698	1x · 1 config	on-demand
NVIDIA L40	$0.86	$0.86	0%	$619	1x · 1 config	on-demand
NVIDIA RTX 6000 Ada	$0.79	$0.82	-3%	$569	1x · 1 config	on-demand
NVIDIA RTX A6000	$0.57	$0.56	+2%	$410	1x–2x · 3 configs	on-demand
NVIDIA RTX A5000	$0.44	$0.27	+63%	$317	1x · 1 config	on-demand

Price history

Massed Compute 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. No price moved by more than 1% between consecutive snapshots so far.

Compare Massed Compute

Massed Compute vs RunPod Community CloudSame GPUs, both prices, who is cheaper on each Massed Compute vs RunPod Secure CloudSame GPUs, both prices, who is cheaper on each Massed Compute vs Vast.aiSame GPUs, both prices, who is cheaper on each Massed Compute vs GPU.aiSame GPUs, both prices, who is cheaper on each Massed Compute vs io.netSame GPUs, both prices, who is cheaper on each Massed Compute 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 Modal11 GPUs · +13.5% vs market Beam10 GPUs · -20.3% vs market

Questions

How much does Massed Compute charge for an H100?

As of 2026-09-18, Massed Compute's on-demand H100 SXM works out to $2.81 per GPU-hour, 20% below the market median of $3.50. That is about $2,023 a month per GPU at 720 hours.

Is Massed Compute cheap?

Across the 12 GPUs it prices, Massed Compute averages 3.6% below the market median, and is cheaper than the median on 7 of them.

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

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

Open Massed Compute →