What can I run on L4?
24 GB VRAMAda LovelaceFP8 Tensor Core 485 teraFLOPs* (*shown with sparsity)72WView matrix for this target →
Low-profile 72 W inference card. Available on Hugging Face Jobs (1x and 4x L4).
Policy by policy
| Policy | Params | Inference memory (sourced, with precision) | On L4 | 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 L4
No measured runs on L4 yet. A run needs runtime, precision, camera count. Contribute one.
Sources
- T1 · upstream documentedvendor-docsverified 2026-10-24 (1d ago)
L4 spec table: FP8 485 TFLOPS with sparsity, 24GB, 72W TDP.
“FP8 Tensor Core 485 teraFLOPs* INT8 Tensor Core 485 TOPs* GPU memory 24GB GPU memory bandwidth 300GB/s NVENC | NVDEC | JPEG decoders 2 | 4 | 4 Max thermal design power (TDP) 72W”
https://www.nvidia.com/en-us/data-center/l4/ - T1 · upstream documentedvendor-docsverified 2026-10-24 (1d ago)
L4 page: powered by the Ada Lovelace architecture.
“The NVIDIA L4 Tensor Core GPU powered by the NVIDIA Ada Lovelace architecture”
https://www.nvidia.com/en-us/data-center/l4/ - T1 · upstream documentedofficial-docsverified 2026-10-24 (1d ago)
Hugging Face Jobs pricing lists L4 flavors (24 GB).
“1x Nvidia L4 8 vCPU 30 GB 24 GB 400 GB $0.80”
https://huggingface.co/docs/hub/jobs-pricing