NVIDIA V100 16GB SXM

Name: NVIDIA V100 16GB SXM
Brand: NVIDIA
Availability: InStock

Data center GPU · Volta

Summary

One of three NVIDIA V100 variants, with 16GB of HBM2 in the SXM2 form factor. For twice the memory, see the V100 32GB SXM.

Launched

2017

VRAM

16 GB

Mem. bandwidth

900 GB/s

On-demand from

Tech specs

VRAM 16 GB HBM2

Memory bandwidth 900 GB/s

Interface SXM

CUDA cores 5,120

Tensor cores 640 (Gen 1)

TDP 300 W

Supported data types

FP64FP32FP16INT8

3 providers · available in 11 countries · lowest price per GPU, per hour

Prices updated 23 October 2026

On-demand

$0.78 – $3.06 /GPU/h

Provider	On-demand	Reserved	Spot
AWS ?	$3.06	—	—
Oracle ?	$2.95	—	—
OVHcloud ?	$0.78	—	—

	Total VRAM	From	16-bit inference	8-bit inference	4-bit inference
1× V100 16GB SXM	16 GB	$0.78/h	Qwen3-4B-Instruct-2507Rio-3.0-Open-MiniNVIDIA-Nemotron-3-Nano-4B-BF16	Qwen3-4B-Instruct-2507Rio-3.0-Open-MiniNVIDIA-Nemotron-3-Nano-4B-BF16	gpt-oss-20bQwen3-4B-Instruct-2507Rio-3.0-Open-Mini
2× V100 16GB SXM	32 GB	$1.57/h	Qwen3-4B-Instruct-2507Rio-3.0-Open-MiniNVIDIA-Nemotron-3-Nano-4B-BF16	gpt-oss-20bQwen3-4B-Instruct-2507Rio-3.0-Open-Mini	GLM-4.7-FlashQwen3-Coder-30B-A3B-InstructNVIDIA-Nemotron-3-Nano-30B-A3B-BF16
4× V100 16GB SXM	64 GB	$3.14/h	gpt-oss-20bQwen3-4B-Instruct-2507Rio-3.0-Open-Mini	GLM-4.7-FlashQwen3-Coder-30B-A3B-InstructNVIDIA-Nemotron-3-Nano-30B-A3B-BF16	GLM-4.5-AirQwen3-Coder-NextNVIDIA-Nemotron-3-Nano-30B-A3B-BF16
8× V100 16GB SXM	128 GB	$23.60/h	GLM-4.7-FlashQwen3-Coder-30B-A3B-InstructNVIDIA-Nemotron-3-Nano-30B-A3B-BF16	GLM-4.5-AirQwen3-Coder-NextNVIDIA-Nemotron-3-Nano-30B-A3B-BF16	DeepSeek-V4-Flashgpt-oss-120bNVIDIA-Nemotron-3-Super-120B-A12B-BF16

Show all configurations

Open-weights models that fit in VRAM. Estimated using 🤗 accelerate, plus approximation for up to 8K context.

Detailed documentation from the manufacturer.