Compare · prices checked 2026-09-03
L40S vs H100 PCIE: specs, price per hour, which to rent
NVIDIA L40S (48 GB, $0.466/hr) against NVIDIA H100 PCIE (80 GB, $2.147/hr): public specs side by side, live fixed prices from our sheet, what fits in each card's VRAM, and a verdict written for real workloads — both are rentable right now.
L40S vs H100 PCIE specifications
Public NVIDIA figures (dense, non-sparsity). The last column is L40S relative to H100 PCIE.
| Spec | L40S | H100 PCIE | Difference |
|---|---|---|---|
| Architecture | Ada Lovelace (2023) | Hopper (2022) | — |
| VRAM | 48 GB GDDR6 | 80 GB HBM2e | −40% |
| Memory bandwidth | 864 GB/s | 2,000 GB/s | −57% |
| FP16 tensor (dense) | 362 TFLOPS | 756 TFLOPS | −52% |
| FP32 | 91.6 TFLOPS | 51.0 TFLOPS | +80% |
| CUDA cores | 18,176 | 14,592 | +25% |
| TDP | 350 W | 350 W | same |
| PCIe · NVLink | Gen 4.0 · no NVLink | Gen 5.0 · no NVLink | — |
| PowerScore (RTX 3090 = 100) | 255 | 532 | −52% |
| Max GPUs per machine | 8× | 8× | — |
L40S vs H100 PCIE price per hour
Fixed rates from our sheet — every on-demand price is the marketplace median × 0.70, rounded down. Monthly = 730 hours.
| Rate | L40S | H100 PCIE | Cheaper |
|---|---|---|---|
| On-demand, per GPU-hour | $0.466 | $2.147 | L40S (−78%) |
| Interruptible, per GPU-hour | $0.233 | $1.073 | L40S |
| Reserved (3 mo), per GPU-hour | $0.302 | $1.395 | L40S |
| On-demand, per month | $340 | $1,567 | L40S |
| Market median (reference) | $0.67 | $3.07 | — |
| $ per 1,000 FP16 TFLOP-hours | $1.29 | $2.84 | L40S (better value) |
| $ per GB of VRAM per hour | $0.0097 | $0.0268 | L40S (better value) |
Try a full month with storage and bandwidth in the GPU cost calculator.
What fits in VRAM: 48 GB vs 80 GB
| Workload | L40S | H100 PCIE |
|---|---|---|
| Largest LLM in FP16, one card | ~14B | ~32B |
| Largest LLM at 4-bit, one card | ~72B | ~123B |
| Flux dev (FP8, ~17 GB) | fits | fits |
| Wan 2.x 14B video (offloaded) | yes | yes |
| 70B 4-bit LLM on one card | yes | yes |
Rules of thumb: ~2.4 GB per billion parameters in FP16 all-in, ~0.62 GB in 4-bit. Full tables in the VRAM guide.
Verdict: which should you rent?
The H100 PCIe has 80 GB of HBM2e, 2 TB/s and roughly double the tensor throughput; the L40S has 48 GB of GDDR6 and costs a lot less. The L40S is the value choice for models under 32B; the H100 PCIe for 70B and throughput-bound serving.
- Cheaper per hour: L40S ($0.466 vs $2.147, −78%).
- More VRAM: H100 PCIE (80 GB vs 48 GB).
- More FP16 throughput: H100 PCIE (about 2.1×).
- Best value per TFLOP-hour: L40S.
- Best value per GB of VRAM: L40S.
- Multi-GPU: L40S over PCIe · H100 PCIE over PCIe.
Related comparisons
- H100 SXM vs H100 PCIE $1.587 vs $2.147 per hour Compare
- H100 PCIE vs A100 PCIE $2.147 vs $0.662 per hour Compare
- RTX 4090 vs L40S $0.262 vs $0.466 per hour Compare
- L40S vs A100 PCIE $0.466 vs $0.662 per hour Compare
- RTX 5090 vs L40S $0.318 vs $0.466 per hour Compare
- RTX PRO 6000 WS vs H100 PCIE $1.097 vs $2.147 per hour Compare
L40S vs H100 PCIE: FAQ
Deeper reading: H100 vs H200 vs B200, RTX 4090 vs RTX 5090, how cloud GPU pricing works.
Is the H100 PCIE faster than the L40S?
On dense FP16 tensor throughput the H100 PCIE leads by about 2.1× (756 vs 362 TFLOPS). Memory bandwidth matters as much for inference: L40S 864 GB/s vs H100 PCIE 2,000 GB/s.
Which is cheaper to rent, the L40S or the H100 PCIE?
The L40S: $0.466/hr on-demand versus $2.147/hr — 78% less. Interruptible rates are $0.233 (L40S) and $1.073 (H100 PCIE). Per TFLOP-hour the better value is the L40S.
Which has more VRAM and what does that change?
The H100 PCIE has 80 GB versus 48 GB. In LLM terms that is roughly a 32B FP16 model (or ~123B in 4-bit) on one card against 14B FP16 (~72B 4-bit). If the model does not fit, speed is irrelevant.
Can I rent both on PowerGPU right now?
Yes — 59 × L40S and 60 × H100 PCIE are online as this page renders, deployable in about 30 seconds, billed per second, paid in crypto with no KYC.