Price floor Every GPU at least 30% below the market median — re-checked against the marketplace weekly.

See the proof

Compare · prices checked 2026-09-03

RTX 4090 vs L40S: specs, price per hour, which to rent

NVIDIA RTX 4090 (24 GB, $0.262/hr) against NVIDIA L40S (48 GB, $0.466/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.

RTX 4090 vs L40S specifications

Public NVIDIA figures (dense, non-sparsity). The last column is RTX 4090 relative to L40S.

SpecRTX 4090L40SDifference
ArchitectureAda Lovelace (2022)Ada Lovelace (2023)
VRAM24 GB GDDR6X48 GB GDDR6−50%
Memory bandwidth1,008 GB/s864 GB/s+17%
FP16 tensor (dense)330 TFLOPS362 TFLOPS−9%
FP3282.6 TFLOPS91.6 TFLOPS−10%
CUDA cores16,38418,176−10%
TDP450 W350 W+29%
PCIe · NVLinkGen 4.0 · no NVLinkGen 4.0 · no NVLink
PowerScore (RTX 3090 = 100)232255−9%
Max GPUs per machine

RTX 4090 vs L40S price per hour

Fixed rates from our sheet — every on-demand price is the marketplace median × 0.70, rounded down. Monthly = 730 hours.

RateRTX 4090L40SCheaper
On-demand, per GPU-hour$0.262$0.466RTX 4090 (−44%)
Interruptible, per GPU-hour$0.131$0.233RTX 4090
Reserved (3 mo), per GPU-hour$0.170$0.302RTX 4090
On-demand, per month$191$340RTX 4090
Market median (reference)$0.37$0.67
$ per 1,000 FP16 TFLOP-hours$0.79$1.29RTX 4090 (better value)
$ per GB of VRAM per hour$0.0109$0.0097L40S (better value)

Try a full month with storage and bandwidth in the GPU cost calculator.

What fits in VRAM: 24 GB vs 48 GB

WorkloadRTX 4090L40S
Largest LLM in FP16, one card~8B~14B
Largest LLM at 4-bit, one card~32B~72B
Flux dev (FP8, ~17 GB)fitsfits
Wan 2.x 14B video (offloaded)yesyes
70B 4-bit LLM on one cardnoyes

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 L40S is the datacenter Ada card: 48 GB, passive cooling, FP8, built for 24/7 duty; the RTX 4090 has similar per-clock throughput, 24 GB and a lower rate. Serve production endpoints on the L40S; run interactive and batch generation on the 4090.

  • Cheaper per hour: RTX 4090 ($0.262 vs $0.466, −44%).
  • More VRAM: L40S (48 GB vs 24 GB).
  • More FP16 throughput: L40S (about 1.1×).
  • Best value per TFLOP-hour: RTX 4090.
  • Best value per GB of VRAM: L40S.
  • Multi-GPU: RTX 4090 over PCIe · L40S over PCIe.
Is the L40S faster than the RTX 4090?

On dense FP16 tensor throughput the L40S leads by about 1.1× (362 vs 330 TFLOPS). Memory bandwidth matters as much for inference: RTX 4090 1,008 GB/s vs L40S 864 GB/s.

Which is cheaper to rent, the RTX 4090 or the L40S?

The RTX 4090: $0.262/hr on-demand versus $0.466/hr — 44% less. Interruptible rates are $0.131 (RTX 4090) and $0.233 (L40S). Per TFLOP-hour the better value is the RTX 4090.

Which has more VRAM and what does that change?

The L40S has 48 GB versus 24 GB. In LLM terms that is roughly a 14B FP16 model (or ~72B in 4-bit) on one card against 8B FP16 (~32B 4-bit). If the model does not fit, speed is irrelevant.

Can I rent both on PowerGPU right now?

Yes — 439 × RTX 4090 and 59 × L40S are online as this page renders, deployable in about 30 seconds, billed per second, paid in crypto with no KYC.

Deploy your first GPU in under a minute

Top up in crypto, benchmark us against your current provider. Per-second billing, fixed prices ≥ 30% below market — cancel by just stopping the instance.