What can I run on A100 40GB?
40 GB VRAMAmpereBFLOAT16 Tensor Core 312 TFLOPS | 624 TFLOPS* (*with sparsity)250W (PCIe) / 400W (SXM)View matrix for this target →
HBM2, PCIe or SXM4. NVIDIA's current A100 product page lists only the 80GB variants; the 40GB figures come from the A100 datasheet. Not offered as a Hugging Face Jobs flavor (Jobs' A100 is the 80 GB part). Many papers say just "A100" without the memory variant; such runs cannot be filed here.
Policy by policy
| Policy | Params | Inference memory (sourced, with precision) | On A100 40GB | 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 A100 40GB
No measured runs on A100 40GB yet. A run needs runtime, precision, camera count. Contribute one.
Sources
- T1 · upstream documentedvendor-docsverified 2026-10-24 (1d ago)
A100 datasheet spec table column order.
“40GB PCIe 80GB PCIe 40GB SXM 80GB SXM”
https://www.nvidia.com/content/dam/en-zz/Solutions/Data-Center/a100/pdf/nvidia-a100-datasheet-us-nvidia-1758950-r4-web.pdf - T1 · upstream documentedvendor-docsverified 2026-10-24 (1d ago)
A100 datasheet GPU Memory row (40GB PCIe, 80GB PCIe, 40GB SXM, 80GB SXM).
“GPU Memory 40GB 80GB 40GB 80GB”
https://www.nvidia.com/content/dam/en-zz/Solutions/Data-Center/a100/pdf/nvidia-a100-datasheet-us-nvidia-1758950-r4-web.pdf - T1 · upstream documentedvendor-docsverified 2026-10-24 (1d ago)
A100 datasheet Max TDP row (40GB PCIe, 80GB PCIe, 40GB SXM, 80GB SXM).
“250W 300W 400W 400W”
https://www.nvidia.com/content/dam/en-zz/Solutions/Data-Center/a100/pdf/nvidia-a100-datasheet-us-nvidia-1758950-r4-web.pdf - T1 · upstream documentedvendor-docsverified 2026-10-24 (1d ago)
A100 datasheet BFLOAT16 Tensor Core figure (dense | sparse), same for all variants.
“312 TFLOPS | 624 TFLOPS*”
https://www.nvidia.com/content/dam/en-zz/Solutions/Data-Center/a100/pdf/nvidia-a100-datasheet-us-nvidia-1758950-r4-web.pdf