GMKtec EVO-X2 (128GB unified)
The $/GB winner: runs 70B-class and quantized big-MoE (V4 Flash tier) that no consumer GPU fits
A100 PCIe cloud pricing, August 2026
Live A100 PCIe quotes (80 GB VRAM) across the providers we track, cheapest first. Marketplace prices are real asks from the Vast.ai order book; secure/on-demand tiers carry datacenter SLAs (what the tiers mean).
Quotes refreshed 2026-08-23
Price floor: $0.442/hr (marketplace) at
Vast.ai.
Rent a A100 PCIe →
| Provider | Tier | $/hr per GPU | Median $/hr | Live offers | |
|---|---|---|---|---|---|
| Vast.ai | marketplace | $0.442 | $0.934 | 29 | Rent |
| RunPod | community | $1.19 | - | - | Rent |
| RunPod | secure | $1.39 | - | - | Rent |
What fits on a single A100 PCIe
Models from our tracked open-weight set that fit in 80 GB, with KV-cache headroom included. Bigger models need multi-GPU nodes (math in the calculator).
| Model | Params | Fits at | VRAM needed | Cheapest API $/1M out |
|---|---|---|---|---|
| GLM-4.7 Flash | 31B | FP8 | 43 GB | compare → |
| Qwen3.6 35B A3B | 36B | FP8 | 50 GB | compare → |
| Qwen3.6 27B | 27.8B | FP8 | 39 GB | compare → |
| Qwen3.5 35B A3B | 36B | FP8 | 50 GB | compare → |
| Qwen3.5 27B | 27.8B | FP8 | 39 GB | compare → |
| Qwen3 32B | 32.8B | FP8 | 46 GB | compare → |
| Qwen3 30B A3B | 30.5B | FP8 | 42 GB | compare → |
| Mistral Small 3.1 | 24B | FP8 | 33 GB | |
| Nemotron 3 Nano | 30B | FP8 | 42 GB | compare → |
| IBM Granite 4.1 30B | 30B | FP8 | 42 GB | |
| IBM Granite 4.1 8B | 8.8B | FP8 | 13 GB | compare → |
| GPT-OSS 20B | 21B | FP8 | 29 GB | compare → |
| Llama 3.1 8B | 8B | FP8 | 11 GB | compare → |
| Llama 3.2 3B | 3.2B | FP8 | 5 GB | compare → |
| Gemma 3 27B | 27B | FP8 | 38 GB | compare → |
| Gemma 3 12B | 12B | FP8 | 17 GB | compare → |
| Phi-4 | 14.7B | FP8 | 21 GB | compare → |
| Mixtral 8x7B | 46.7B | FP8 | 65 GB | compare → |
| DeepSeek R1 Distill Qwen 32B | 32.8B | FP8 | 46 GB | compare → |
| GLM-4.5 Air | 106B | INT4 | 73 GB | compare → |
| Llama 4 Scout | 109B | INT4 | 75 GB | compare → |
| Llama 3.3 70B | 70B | INT4 | 49 GB | compare → |
| DeepSeek R1 Distill Llama 70B | 70B | INT4 | 49 GB | compare → |
Can't buy a A100 PCIe? The desk-side alternatives
A100 PCIe cards only ship in servers, but the "own your inference box" itch has real answers: run the economics in the calculator, then look at what this audience actually buys:
NVIDIA RTX 5090 (32GB)
Bandwidth-per-dollar king for the A3B-MoE and 27-32B dense workhorses
NVIDIA RTX PRO 6000 Blackwell (96GB)
The startup standard: only sub-$10K single card that runs 70B+ comfortably
As an Amazon Associate we earn from qualifying purchases · hardware links may be referral links · picks are editorial, not paid · disclosure
FAQ
How much does it cost to rent a A100 PCIe?
As of 2026-08-23, A100 PCIe rentals start at $0.442/hr (marketplace tier at Vast.ai). Datacenter capacity with SLAs typically costs more than community or marketplace hardware.
What can you run on a A100 PCIe?
With 80 GB of VRAM, a single A100 PCIe fits models up to roughly 57B parameters at FP8 or 114B at INT4 quantization, including KV-cache headroom.
Cite or embed today's floor
Live badge for a README. It updates itself with every daily refresh:
[](https://llmhosting.ai/gpus/a100-pcie)
Citation: A100 PCIe rental floor $0.442/hr (llmhosting.ai, 2026-08-23). Free to reuse with a link back.