NVIDIA V100 SXM2 32GB
The V100 pioneered Tensor Cores and mixed-precision training with 32GB HBM2 memory. A landmark GPU that defined modern AI infrastructure, still deployed for many workloads.
VRAM
32 GB
Memory
HBM2
Bandwidth
900 GB/s
FP16
125 TF
TDP
300 W
Memory and compute
Architecture and power
Notes
Previous gen flagship
Models that may fit on NVIDIA V100 SXM2 32GB
Estimates based on INT8 quantization. Actual fit depends on framework and batch size.
More GPUs by NVIDIA
The manufacturer's other cards in the catalog, largest memory first, with bandwidth and power where published.
Frequently asked questions about NVIDIA V100 SXM2 32GB
Answered from the entry's own figures: memory, which models fit, bandwidth, power and the card's class.
NVIDIA V100 SXM2 32GB has 32 GB of HBM2 at 900 GB/s. At INT8 a model's weights take about one byte per parameter, so the card holds roughly a 25B-parameter model with room for context; larger models need several cards or a lower precision.
From the catalog's estimates at INT8, Qwen 2.5 14B Instruct AWQ, Llama Nemotron Embed Vl 1B V2, GLM Z1 9B 0414 and Nvidia Nemotron Nano 12B V2 VL BF16 fit on a single NVIDIA V100 SXM2 32GB with their default context. The list on this page shows the estimated memory each takes; the capacity planner sizes any model against this card for your own context length, batch size and request rate.
900 GB/s. Bandwidth bounds how fast a model generates tokens, because every token reads the whole set of weights and the KV cache from memory; at this rate a 25B model at INT8 could be read on the order of 35 times a second on one card, before batching and framework efficiency.
NVIDIA V100 SXM2 32GB has a TDP of 300 W, with a maximum of 300 W, in the SXM2 form factor. Budget the TDP per card plus host overhead when sizing a server's power and cooling.
NVIDIA V100 SXM2 32GB is a datacenter accelerator, meant for servers and multi-GPU serving, built on the Volta architecture and released in 2018. It supports a multi-GPU interconnect at 300 GB/s, so a model larger than one card can be split across several.
Specifications from the manufacturer's published material; a figure that is not published is shown as such, and a derived one is explained in the notes.
Added Jan 25, 2026 · Last updated Jan 25, 2026
Explore more
Companion tools that draw on the same catalog and routing engine.
Put intelligence in the middle.
One gateway in front of every model, with your policies applied and every decision on record. Start with $5 of credit and 5,000 routing decisions a month, no card required.