---
title: "RTX 4090 vs A100 80GB for Inference (Sep 2026)"
description: "Compare RTX 4090 and A100 80GB cloud pricing, VRAM and estimated model fit using sourced offers."
canonical: https://vpsledger.com/gpu/rtx-4090-vs-a100-80gb/
verified: 2026-10-23
format: text/markdown
html: https://vpsledger.com/gpu/rtx-4090-vs-a100-80gb/
---

# RTX 4090 vs A100 80GB for Inference (Sep 2026)

> Markdown alternate of <https://vpsledger.com/gpu/rtx-4090-vs-a100-80gb/>. Generated at build time from the
> same dataset as the HTML page; prices verified 2026-10-23. Data is a build-time
> snapshot — no live API, no auth. Machine entry point: <https://vpsledger.com/ai/>.

[GPU cloud](/gpu/) / RTX 4090 vs A100 80GB

# RTX 4090 vs A100 80GB for inference

VRAM: [RTX 4090](/gpu/rtx-4090/) 24 GB; [A100 80GB](/gpu/a100-80gb/) 80 GB. 70B 4-bit estimated memory with 20% headroom: 42.0 GB. Throughput depends on model and workload; enter a measured rate in the [cost calculator](/tools/llm-inference-cost-calculator/).

| GPU | Provider | VRAM | GPU count | USD/hour | $/GB/hr | Billing | Type | Verified | Source |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| [RTX 4090](/gpu/rtx-4090/) | [salad](/gpu/providers/salad/) | 24 GB | 1 | $0.16lowest priority | $0.007 | per-second | interruptible | 2026-09-26 | [Official price ↗](https://salad.com/pricing/) |
| [RTX 4090](/gpu/rtx-4090/) | [tensordock](/gpu/providers/tensordock/) | 24 GB | 1 | from $0.35 | $0.015 | hourly | on-demand | 2026-09-26 | [Official price ↗](https://marketplace.tensordock.com/) |
| [A100 80GB](/gpu/a100-80gb/) | [hyperstack](/gpu/providers/hyperstack/) | 80 GB | 1 | $1.35 | $0.017 | per-minute | on-demand | 2026-09-26 | [Official price ↗](https://www.hyperstack.cloud/gpu-pricing) |
| [A100 80GB](/gpu/a100-80gb/) | [runpod](/gpu/providers/runpod/) | 80 GB | 1 | $1.59 | $0.020 | per-second | on-demand | 2026-09-26 | [Official price ↗](https://www.runpod.io/pricing) |
| [A100 80GB](/gpu/a100-80gb/) | [tensordock](/gpu/providers/tensordock/) | 80 GB | 1 | from $1.80 | $0.022 | hourly | on-demand | 2026-09-26 | [Official price ↗](https://marketplace.tensordock.com/) |
| [RTX 4090](/gpu/rtx-4090/) | [runpod](/gpu/providers/runpod/) | 24 GB | 1 | $0.74 | $0.031 | per-second | on-demand | 2026-09-26 | [Official price ↗](https://www.runpod.io/pricing) |
| [A100 80GB](/gpu/a100-80gb/) | [modal](/gpu/providers/modal/) | 80 GB | 1 | $2.50GPU only | $0.031 | per-second | on-demand | 2026-09-26 | [Official price ↗](https://modal.com/pricing) |
| [A100 80GB](/gpu/a100-80gb/) | [ovhcloud](/gpu/providers/ovhcloud/) | 80 GB | 1 | $3.07 | $0.038 | hourly | on-demand | 2026-09-26 | [Official price ↗](https://www.ovhcloud.com/en/public-cloud/prices/) |
| [A100 80GB](/gpu/a100-80gb/) | [digitalocean](/gpu/providers/digitalocean/) | 80 GB | 1 | $3.18 | $0.040 | hourly | on-demand | 2026-09-26 | [Official price ↗](https://docs.digitalocean.com/products/paperspace/pricing/) |

Each price has an official source and verification date. Rates and availability change; affiliate links, if added later, will be marked sponsored.