What can I run on L40S?
48 GB VRAMAda LovelaceFP8 Tensor Core 733 I 1,466* (*with sparsity)350WView matrix for this target →
Not the same part as the L40 (see compute "l40"). Available on Hugging Face Jobs (1x, 4x, 8x).
Policy by policy
| Policy | Params | Inference memory (sourced, with precision) | On L40S | Best measured |
|---|---|---|---|---|
| ACT Imitation | 80M | 211 MB measured fp32 | no data | |
| Diffusion Policy Imitation | — | 1.12 GB measured fp32 | no data | |
| EO-1 VLA | 3B | ≥6.5 GB | no data | |
| Evo-1 VLA | 770M | — | no data | |
| Fast-WAM World model | 6B | — | no data | |
| GR00T N1.7 VLA | 3B | ≥16 GB | no data | |
| HIL-SERL RL | — | — | no data | |
| LingBot-VA World model | 5.3B | ≥18 GB | no data | |
| MolmoAct2 VLA | — | 12.1 GB measured bf16 | no data | |
| Multitask DiT Imitation | 450M | — | no data | |
| OpenVLA VLA | 7.5B | 15 GB measured bf16 | no data | |
| OpenVLA-OFT VLA | — | ≥16 GB | no data | |
| SmolVLA VLA | 450M | 1.75 GB measured fp32 | no data | |
| TD-MPC RL | — | — | no data | |
| VLA-JEPA VLA | — | — | no data | |
| VQ-BeT Imitation | — | — | no data | |
| WALL-OSS VLA | — | — | no data | |
| X-VLA VLA | 900M | — | no data | |
| π0 VLA | 3.3B | 13.32 GB measured fp32 | no data | |
| π0-FAST VLA | — | ≥8 GB | no data | |
| π0.5 VLA | — | ≥8 GB | no data |
“Exceeds memory” compares a policy's upstream-stated minimum inference memory (never a measured peak, which is precision-specific) with this target's VRAM. It is arithmetic, not observation, and is labelled inferred. Quantised or split runtimes can change the answer; a measured run always wins.
All measured runs on L40S
No measured runs on L40S yet. A run needs runtime, precision, camera count. Contribute one.
Sources
- T1 · upstream documentedvendor-docsverified 2026-10-24 (1d ago)
L40S spec table: Ada Lovelace, 48GB GDDR6 with ECC.
“GPU Architecture NVIDIA Ada Lovelace architecture GPU Memory 48GB GDDR6 with ECC”
https://www.nvidia.com/en-us/data-center/l40s/ - T1 · upstream documentedvendor-docsverified 2026-10-24 (1d ago)
L40S spec table: FP8 Tensor Core 733 dense / 1,466 with sparsity TFLOPS.
“FP8 Tensor Core 733 I 1,466*”
https://www.nvidia.com/en-us/data-center/l40s/ - T1 · upstream documentedvendor-docsverified 2026-10-24 (1d ago)
L40S spec table: max power consumption 350W.
“Max Power Consumption 350W”
https://www.nvidia.com/en-us/data-center/l40s/ - T1 · upstream documentedofficial-docsverified 2026-10-24 (1d ago)
Hugging Face Jobs pricing lists L40S flavors (48 GB).
“1x Nvidia L40S 8 vCPU 62 GB 48 GB 380 GB $1.80”
https://huggingface.co/docs/hub/jobs-pricing