Model provider cost

Host Qwen2.5 72B Instruct on Vast.ai

Qwen2.5 72B Instruct needs 1x 80GB+ GPU, and Vast.ai's current cheapest qualifying row is A100 SXM4 at $1.05/hr.

1x 80GB+ GPU 72B params Premium multilingual Tongyi Qianwen License
Cheapest on this provider
$1.05/hr
A100 SXM4
Monthly estimate
$763/mo
730 hours at the current median
VRAM baseline
80GB
1x 80GB+ GPU
Qualifying rows
8
Updated Jul 10, 2026

Vast.ai rows that can host Qwen2.5 72B Instruct

The cheapest tracked way to host Qwen2.5 72B Instruct on Vast.ai is A100 SXM4 at $1.05/hr. Vast.ai is currently tied for the cheapest tracked market setup for this model.

Price source Vast.ai marketplace offers Marketplace aggregate; quality-eligible offers feed the summary price.
GPU VRAM Per GPU Estimated hourly Estimated monthly Offers Updated
A100 SXM4 80GB $1.05/hr $1.05/hr $763/mo 1 Jul 7, 2026
Vast.ai marketplace offers 1 offer · Jul 7, 2026 global aggregate
A100 PCIE 80GB $1.27/hr $1.27/hr $926/mo 1 Jul 10, 2026
Vast.ai marketplace offers 1 offer · Jul 10, 2026 global aggregate
H100 PCIE 80GB $2.13/hr $2.13/hr $1,557/mo 1 Jul 5, 2026
Vast.ai marketplace offers 1 offer · Jul 5, 2026 global aggregate
H100 SXM 80GB $2.24/hr $2.24/hr $1,632/mo 2 Jul 10, 2026
Vast.ai marketplace offers 2 offers · Jul 10, 2026 global aggregate
H100 NVL 94GB $2.59/hr $2.59/hr $1,890/mo 1 Jul 10, 2026
Vast.ai marketplace offers 1 offer · Jul 10, 2026 global aggregate
H200 NVL 141GB $2.93/hr $2.93/hr $2,142/mo 3 Jul 10, 2026
Vast.ai marketplace offers 3 offers · Jul 10, 2026 global aggregate
H200 141GB $3.75/hr $3.75/hr $2,739/mo 7 Jul 10, 2026
Vast.ai marketplace offers 7 offers · Jul 10, 2026 global aggregate
B200 192GB $8.13/hr $8.13/hr $5,937/mo 2 Jul 10, 2026
Vast.ai marketplace offers 2 offers · Jul 10, 2026 global aggregate

Why this setup does or does not fit

VRAM floor

1x 80GB+ GPU

1x 80GB GPU minimum; 2x 80GB for healthier serving margins. Long prompts, batching, and KV cache can require extra headroom.

Model quality

Premium multilingual

Premium open-weight quality with wide language coverage, but it firmly lives in 80GB-class infrastructure.

Operational note

Qwen 72B

Best suited to teams that want premium open-weight quality with wide language coverage.

Qwen2.5 72B Instruct on Vast.ai FAQ

Can I host Qwen2.5 72B Instruct on Vast.ai?

The cheapest tracked way to host Qwen2.5 72B Instruct on Vast.ai is A100 SXM4 at $1.05/hr.

What GPU memory does Qwen2.5 72B Instruct need?

Our baseline for Qwen2.5 72B Instruct is 1x 80GB+ GPU. The practical recommendation is 1x 80GB GPU minimum; 2x 80GB for healthier serving margins.

Is Vast.ai the cheapest provider for Qwen2.5 72B Instruct?

Vast.ai is currently tied for the cheapest tracked market setup for this model.

How fresh is this Vast.ai Qwen2.5 72B Instruct cost page?

This page recalculates from the latest tracked on-demand rows. The freshest qualifying Vast.ai row shown here is from Jul 10, 2026.

Compare this setup