What can I run on A100 80GB?
80 GB VRAMAmpereBFLOAT16 Tensor Core 312 TFLOPS | 624 TFLOPS* (*with sparsity)300W (PCIe) / 400W (SXM)View matrix for this target →
HBM2e, PCIe or SXM4. Available on Hugging Face Jobs as the "a100-large" flavor (1x, 4x, 8x).
Policy by policy
| Policy | Params | Inference memory (sourced, with precision) | On A100 80GB | 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 80GB
No measured runs on A100 80GB yet. A run needs runtime, precision, camera count. Contribute one.
Sources
- T1 · upstream documentedvendor-docsverified 2026-10-24 (1d ago)
A100 product page spec table (80GB PCIe, 80GB SXM): memory, bandwidth, TDP.
“GPU Memory 80GB HBM2e 80GB HBM2e GPU Memory Bandwidth 1,935 GB/s 2,039 GB/s Max Thermal Design Power (TDP) 300W 400W ***”
https://www.nvidia.com/en-us/data-center/a100/ - T1 · upstream documentedvendor-docsverified 2026-10-24 (1d ago)
A100 product page: BFLOAT16 Tensor Core 312 TFLOPS dense, 624 with sparsity.
“BFLOAT16 Tensor Core 312 TFLOPS | 624 TFLOPS*”
https://www.nvidia.com/en-us/data-center/a100/ - T1 · upstream documentedofficial-docsverified 2026-10-24 (1d ago)
Hugging Face Jobs pricing lists an A100 flavor with 80 GB GPU memory.
“Nvidia A100 - large 12 vCPU 142 GB 80 GB 1000 GB $2.50”
https://huggingface.co/docs/hub/jobs-pricing