H200 vs L40S: Specs, VRAM & Price
Short answer: choose the H200 when 141 GB of VRAM is the gating requirement. Choose the L40S when 48 GB is enough for the workload and the lower hourly rate points that way.
The H200 has 141 GB of VRAM; the L40S has 48 GB.
You can rent both by the hour, no purchase required. H200 from $5.05/GPU/hr; L40S from $0.844/GPU/hr. The L40S is 83% cheaper at the entry rate.
H200
Good for training and serving frontier-scale LLMs
L40S
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 | H200 | L40S |
|---|---|---|
| VRAM | 141 GB | 48 GB |
| Memory bandwidth | 4.8 TB/s | 864 GB/s |
| Architecture | Hopper | Ada Lovelace |
| Compute capability | 9.0 | 8.9 |
| Precisions in hardware | FP32, FP16, BF16, FP8, INT4 | FP32, FP16, BF16, FP8, INT4 |
| Peak FP16/BF16 tensor TFLOPS | 989 TFLOPS | 362 TFLOPS |
| Peak FP8 tensor TFLOPS | 1,979 TFLOPS | 733 TFLOPS |
| NVLink / multi-GPU interconnect | NVLink 4, 900 GB/s bidirectional | – |
| Max board power (TDP) | Up to 700W (configurable) | 350W |
| Form factor | SXM | PCIe |
| Regions | 3 | 4 |
On-demand price
| Rate | H200 | L40S |
|---|---|---|
| Lowest per GPU/hr | $5.05/GPU/hr | $1.07/GPU/hr |
Which is better for AI: H200 or L40S?
Choose the H200 when 141 GB of VRAM is the gating requirement. Choose the L40S when 48 GB is enough for the workload and the lower hourly rate points that way.
H200 vs L40S: common questions
Is the H200 or the L40S better for AI?
Short answer: choose the H200 when 141 GB of VRAM is the gating requirement. Choose the L40S when 48 GB is enough for the workload and the lower hourly rate points that way.
Is the H200 or the L40S cheaper to rent?
On Aquanode's live marketplace the H200 starts at $5.05/GPU/hr (median $5.05/GPU/hr) and the L40S starts at $0.844/GPU/hr (median $2.36/GPU/hr). The L40S is the cheaper of the two at the entry rate, by 83%.
What is the difference between the H200 and the L40S?
The H200 has 141 GB of VRAM against the L40S's 48 GB; the H200 is a Hopper part and the L40S is Ada Lovelace (compute capability 9.0 vs 8.9); both run BF16, FP8, INT4 workloads in hardware. On price, the H200 lists from $5.05/GPU/hr and the L40S from $0.844/GPU/hr.
How widely available are the H200 and the L40S?
The H200 is listed in 3 regions and the L40S in 4 regions right now.
How much does 1,000 GPU-hours cost on the H200 vs the L40S?
At the lowest rates listed today, 1,000 GPU-hours costs $5,050 on the H200 and $844 on the L40S, a difference of $4,206 for the same runtime. Rates are per GPU per hour and update hourly.
How much VRAM does the H200 have compared to the L40S?
The H200 has 141 GB of VRAM; the L40S has 48 GB.
Does the H200 or the L40S support NVLink?
The H200 supports NVLink 4, 900 GB/s bidirectional; the L40S 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 H200 page and L40S 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 H200 VRAM calculator and the L40S VRAM calculator, see vendor-published throughput in the GPU benchmarks and specs table, or browse every model by generation in the GPU index.
More H200 comparisons
More L40S comparisons
Related reading: H200 pricing and specs, NVIDIA H200 guide, H100 vs H200, H200 vs B200 vs GB200, and H100 and H200: SXM vs NVL vs PCIe.
