NVIDIA A100 SXM 40GB
The original A100 introduced the Ampere architecture with 3rd-gen Tensor Cores and 40GB HBM2e memory. Widely deployed across major cloud providers for AI and scientific computing.
VRAM
40 GB
Memory
HBM2e
Bandwidth
1,555 GB/s
FP16
312 TF
TDP
400 W
Memory and compute
Architecture and power
Notes
Original A100
Models that may fit on NVIDIA A100 SXM 40GB
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 A100 SXM 40GB
Answered from the entry's own figures: memory, which models fit, bandwidth, power and the card's class.
NVIDIA A100 SXM 40GB has 40 GB of HBM2e at 1,555 GB/s. At INT8 a model's weights take about one byte per parameter, so the card holds roughly a 32B-parameter model with room for context; larger models need several cards or a lower precision.
From the catalog's estimates at INT8, Gemma 4 31B IT, Aya Vision 32B, Llama Nemotron Embed Vl 1B V2 and GLM Z1 9B 0414 fit on a single NVIDIA A100 SXM 40GB 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.
1,555 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 32B model at INT8 could be read on the order of 49 times a second on one card, before batching and framework efficiency.
NVIDIA A100 SXM 40GB has a TDP of 400 W, with a maximum of 400 W, in the SXM4 form factor. Budget the TDP per card plus host overhead when sizing a server's power and cooling.
NVIDIA A100 SXM 40GB is a datacenter accelerator, meant for servers and multi-GPU serving, built on the Ampere architecture and released in 2020. It supports a multi-GPU interconnect at 600 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.