A10 cloud pricing, August 2026

Live A10 quotes (24 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: $0.241/hr (marketplace) at Vast.ai. Rent a A10 →
Provider Tier $/hr per GPU Median $/hr Live offers
Vast.ai marketplace $0.241 $0.241 8 Rent

What fits on a single A10

Models from our tracked open-weight set that fit in 24 GB, with KV-cache headroom included. Bigger models need multi-GPU nodes (math in the calculator).

ModelParamsFits atVRAM neededCheapest API $/1M out
IBM Granite 4.1 8B 8.8B FP8 13 GB compare →
Llama 3.1 8B 8B FP8 11 GB compare →
Llama 3.2 3B 3.2B FP8 5 GB compare →
Gemma 3 12B 12B FP8 17 GB compare →
Phi-4 14.7B FP8 21 GB compare →
GLM-4.7 Flash 31B INT4 22 GB compare →
Qwen3.6 27B 27.8B INT4 20 GB compare →
Qwen3.5 27B 27.8B INT4 20 GB compare →
Qwen3 32B 32.8B INT4 23 GB compare →
Qwen3 30B A3B 30.5B INT4 21 GB compare →
Mistral Small 3.1 24B INT4 17 GB
Nemotron 3 Nano 30B INT4 21 GB compare →
IBM Granite 4.1 30B 30B INT4 21 GB
GPT-OSS 20B 21B INT4 15 GB compare →
Gemma 3 27B 27B INT4 19 GB compare →
DeepSeek R1 Distill Qwen 32B 32.8B INT4 23 GB compare →

FAQ

How much does it cost to rent a A10?

As of 2026-08-23, A10 rentals start at $0.241/hr (marketplace tier at Vast.ai). Datacenter capacity with SLAs typically costs more than community or marketplace hardware.

What can you run on a A10?

With 24 GB of VRAM, a single A10 fits models up to roughly 17B parameters at FP8 or 34B 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:

A10 rental floor badge

[![A10 rental floor](https://llmhosting.ai/badge/a10.svg)](https://llmhosting.ai/gpus/a10)

Citation: A10 rental floor $0.241/hr (llmhosting.ai, 2026-08-23). Free to reuse with a link back.

Daily A10 price history →