A100 vs L40: Specs, VRAM & Price
Short answer: choose the A100 when 80 GB of VRAM is the gating requirement. Choose the L40 when 48 GB is enough for the workload and the lower hourly rate points that way.
The A100 has 80 GB of VRAM; the L40 has 48 GB.
You can rent both by the hour, no purchase required. A100 from $1.26/GPU/hr; L40 from $0.850/GPU/hr. The L40 is 33% cheaper at the entry rate.
A100
Good for training and inference on models that don't need FP8 kernels
L40
Good for fine-tuning mid-size models and high-throughput inference
Last updated: 2026-11-03 UTCRefreshes every 6 hours
Specs side by side
| Spec | A100 | L40 |
|---|---|---|
| VRAM | 80 GB | 48 GB |
| Memory bandwidth | 2,039 GB/s | 864 GB/s |
| Architecture | Ampere | Ada Lovelace |
| Compute capability | 8.0 | 8.9 |
| Precisions in hardware | FP32, FP16, BF16, INT4 | FP32, FP16, BF16, FP8, INT4 |
| Peak FP16/BF16 tensor TFLOPS | 312 TFLOPS | 181.05 TFLOPS |
| Peak FP8 tensor TFLOPS | – | 362 TFLOPS |
| NVLink / multi-GPU interconnect | NVLink 3, 600 GB/s | – |
| Max board power (TDP) | 400W (SXM) | 300W |
| Form factor | SXM4 | – |
| Regions | 5 | 2 |
On-demand price
| Rate | A100 | L40 |
|---|---|---|
| Lowest per GPU/hr | $1.49/GPU/hr | $0.850/GPU/hr |
Which is better for AI: A100 or L40?
Choose the A100 when 80 GB of VRAM is the gating requirement. Choose the L40 when 48 GB is enough for the workload and the lower hourly rate points that way.
A100 vs L40: common questions
Is the A100 or the L40 better for AI?
Short answer: choose the A100 when 80 GB of VRAM is the gating requirement. Choose the L40 when 48 GB is enough for the workload and the lower hourly rate points that way.
Is the A100 or the L40 cheaper to rent?
On Aquanode's live marketplace the A100 starts at $1.26/GPU/hr (median $1.52/GPU/hr) and the L40 starts at $0.850/GPU/hr (median $1.03/GPU/hr). The L40 is the cheaper of the two at the entry rate, by 33%.
What is the difference between the A100 and the L40?
The A100 has 80 GB of VRAM against the L40's 48 GB; the A100 is an Ampere part and the L40 is Ada Lovelace (compute capability 8.0 vs 8.9); only the L40 supports FP8 compute. On price, the A100 lists from $1.26/GPU/hr and the L40 from $0.850/GPU/hr.
How widely available are the A100 and the L40?
The A100 is listed in 5 regions and the L40 in 2 regions right now.
How much does 1,000 GPU-hours cost on the A100 vs the L40?
At the lowest rates listed today, 1,000 GPU-hours costs $1,264 on the A100 and $850 on the L40, a difference of $414 for the same runtime. Rates are per GPU per hour and update hourly.
How much VRAM does the A100 have compared to the L40?
The A100 has 80 GB of VRAM; the L40 has 48 GB.
Does the A100 or the L40 support NVLink?
The A100 supports NVLink 3, 600 GB/s; the L40 has no dedicated GPU-to-GPU interconnect.
How this comparison is calculated
Every price is normalized to a per-GPU hourly rate using the same pipeline as every other pricing surface on Aquanode, and only the cheapest qualifying offer per provider is shown. A dash means that provider does not currently list that GPU.
Architecture, compute capability and supported precisions come from each vendor's published datasheet for that generation, not from the marketplace feed. This page regenerates at most once per hour.
Memory bandwidth, tensor TFLOPS, NVLink/interconnect and max board power are the same verified-from-datasheet figures shown on each model's own A100 page and L40 page, which link the primary vendor source for that model. A dash here means Aquanode hasn't verified that figure from a primary source yet, never a guess.
Go further
Check what fits in each card's memory with the A100 VRAM calculator and the L40 VRAM calculator, see vendor-published throughput in the GPU benchmarks and specs table, or browse every model by generation in the GPU index.
More A100 comparisons
More L40 comparisons
Related reading: A100 pricing and specs, A100 vs H100, A100 vs V100, and The best GPUs for AI, ranked.
