A100 40GB vs A100 80GB
The A100 40GB and the A100 80GB are both data centre GPUs we supply tested from Hong Kong, and the figures below are the same ones published on each product page. They share the same supply and warranty terms and separate on memory, interface, architecture, so the decision is less about "which is better" and more about which of those differences your platform or workload can actually use.
Nothing on this page is a price: used and refurbished hardware is repriced weekly, so both are quoted on request against confirmed stock with the date the quote holds until. If you are replacing a part, send the platform and we will confirm the population before you commit.
Side by side
A100 40GB vs A100 80GB specifications
| Specification | A100 40GB | A100 80GB |
|---|---|---|
| Memory | 40GB HBM2 ECC, 1,555 GB/s | 80GB HBM2e with ECC, 1,935 GB/s on PCIe; 2,039 GB/s on SXM4 |
| Interface | PCIe Gen4 x16, dual-slot passive (250W); SXM4 400W | PCIe Gen4 x16, dual-slot passive (300W); SXM4 400W |
| Architecture | Ampere GA100, 6,912 CUDA cores, 432 Tensor cores (3rd gen) | Ampere GA100, 6,912 CUDA cores, 432 third-gen Tensor cores |
| Compute | FP16 312 TFLOPS / TF32 156 TFLOPS / FP32 19.5 TFLOPS | FP16-BF16 Tensor 312 TFLOPS / TF32 156 TFLOPS / FP32 19.5 TFLOPS |
| MIG | Up to 7 instances (5GB each) | Up to 7 instances (10GB each) |
| NVLink | PCIe: 2-link bridge; SXM4: 12 links, 600 GB/s | PCIe: 2-way bridge; SXM4: 12 links, 600 GB/s |
| Status | Production ended Feb 2024 — secondary market supply | Production discontinued — secondary-market supply only |
| Model | NVIDIA A100 40GB PCIe (900-21001-0000-000); SXM4 variant available | NVIDIA A100 80GB PCIe; SXM4 variant available |
Rows that differ are highlighted. Figures are the same ones published on each product page; where a figure is community-sourced rather than vendor-published it is stated on that page. Confirm every part against your build sheet when ordering.
Where they differ
- ·Memory — A100 40GB: 40GB HBM2 ECC, 1,555 GB/s; A100 80GB: 80GB HBM2e with ECC, 1,935 GB/s on PCIe; 2,039 GB/s on SXM4.
- ·Interface — A100 40GB: PCIe Gen4 x16, dual-slot passive (250W); SXM4 400W; A100 80GB: PCIe Gen4 x16, dual-slot passive (300W); SXM4 400W.
- ·Architecture — A100 40GB: Ampere GA100, 6,912 CUDA cores, 432 Tensor cores (3rd gen); A100 80GB: Ampere GA100, 6,912 CUDA cores, 432 third-gen Tensor cores.
- ·Compute — A100 40GB: FP16 312 TFLOPS / TF32 156 TFLOPS / FP32 19.5 TFLOPS; A100 80GB: FP16-BF16 Tensor 312 TFLOPS / TF32 156 TFLOPS / FP32 19.5 TFLOPS.
- ·MIG — A100 40GB: Up to 7 instances (5GB each); A100 80GB: Up to 7 instances (10GB each).
- ·NVLink — A100 40GB: PCIe: 2-link bridge; SXM4: 12 links, 600 GB/s; A100 80GB: PCIe: 2-way bridge; SXM4: 12 links, 600 GB/s.
Decision
Which one to buy
Data centre GPUs are chosen by memory footprint per job and by the deployment you already have. More memory per card means bigger models, larger batches and fewer cards for the same workload; less memory per card is often the better buy when you scale out across many nodes. Memory bandwidth and compute format matter for the workload — FP8 and BF16 throughput for inference, FP64 for simulation — and the power envelope decides how many cards fit per chassis. Check the form factor and cooling as well: a passive server card and an actively cooled workstation card are not interchangeable.
Choose the A100 40GB if
- ·Memory: 40GB HBM2 ECC, 1,555 GB/s
- ·Interface: PCIe Gen4 x16, dual-slot passive (250W); SXM4 400W
- ·Architecture: Ampere GA100, 6,912 CUDA cores, 432 Tensor cores (3rd gen)
Choose the A100 80GB if
- ·Memory: 80GB HBM2e with ECC, 1,935 GB/s on PCIe; 2,039 GB/s on SXM4
- ·Interface: PCIe Gen4 x16, dual-slot passive (300W); SXM4 400W
- ·Architecture: Ampere GA100, 6,912 CUDA cores, 432 third-gen Tensor cores
Photos
What the two look like
A100 40GB
Photo from the A100 40GB page. Every unit's label is read against your order before dispatch.
A100 80GB
Photo from the A100 80GB page. Every unit's label is read against your order before dispatch.
Frequently asked questions
How much do the A100 40GB and the A100 80GB cost?
We do not publish prices for either: secondary-market hardware is repriced weekly. Send the quantity, the platform and the condition you want and we quote both against confirmed stock, with the date the figure holds until.
What is the main difference between the A100 40GB and the A100 80GB?
Memory (A100 40GB: 40GB HBM2 ECC, 1,555 GB/s; A100 80GB: 80GB HBM2e with ECC, 1,935 GB/s on PCIe; 2,039 GB/s on SXM4); Interface (A100 40GB: PCIe Gen4 x16, dual-slot passive (250W); SXM4 400W; A100 80GB: PCIe Gen4 x16, dual-slot passive (300W); SXM4 400W); Architecture (A100 40GB: Ampere GA100, 6,912 CUDA cores, 432 Tensor cores (3rd gen); A100 80GB: Ampere GA100, 6,912 CUDA cores, 432 third-gen Tensor cores).
Can I use the A100 40GB and the A100 80GB in the same system?
They can share a server if the power and slot budget allows it, but they target different jobs: A100 40GB and A100 80GB differ mainly on Memory and Interface. Mixed GPU models in one host is a driver/CUDA compatibility decision, not a hardware one.
Which one should I buy?
Buy the one whose strong points match the job: see the "Choose" section above. If you are replacing an existing part, send the platform or the old part number and we will confirm compatibility before you order.
What condition are they in, and do you ship worldwide?
Both are supplied tested with a 1-year written warranty. Condition is stated line by line before you order — new, decommissioned pull or OEM tray — and we ship worldwide from the Hong Kong warehouse with full export documentation, typically 3–7 days by air.
Get a quote for either — or both
Tell us the quantity, the platform and the condition you need. We confirm stock and put a firm figure in writing with the date it holds until.
Request a QuoteMore Data Center GPUs · All comparisons · A100 40GB · A100 80GB