V100 VRAM: 16 GB or 32GB HBM2, and what fits in it

Volta. 16 GB VRAM, verified from the vendor datasheet. On-demand rate from $0.110/hr, refreshed every 6 hours.

16 GB
VRAM
Volta
Architecture
$0.110/hr
From
or 32GB HBM2
Memory
Last updated: 2026-11-22 UTCRefreshes every 6 hours

Models that fit at FP16 (16 GB)

Models that fit at INT4 (quantized, 16 GB)

This GPU's hardware doesn't support INT4-class serving kernels (AWQ/GPTQ/Marlin), so no INT4 fit list applies.

All models that fit in 16 GB: the open models whose weights and overhead fit, at native, FP8 and INT4 precision.

Live pricing

$0.110/hr on-demand rate, 3 regions with capacity, refreshed every 6 hours.

V100 guides

Start ComfyUI on a rented GPU.

© 2026 Aquanode. All rights reserved.

All trademarks, logos and brand names are the property of their respective owners.