What can I run on A10G (AWS)?
24 GB VRAMAmpereView matrix for this target →
Cloud-only AWS variant of the A10 (EC2 G5 instances); NVIDIA publishes no standalone A10G spec page, and its specs differ from the retail A10, so no TOPS figure is given here. Available on Hugging Face Jobs (a10g-small, a10g-large, 2x and 4x large).
Policy by policy
| Policy | Params | Inference memory (sourced, with precision) | On A10G (AWS) | 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 A10G (AWS)
No measured runs on A10G (AWS) yet. A run needs runtime, precision, camera count. Contribute one.
Sources
- T1 · upstream documentedvendor-docsverified 2026-10-24 (1d ago)
AWS EC2 G5 page: A10G Tensor Core GPUs with 24 GB memory per GPU.
“Each instance features up to 8 A10G Tensor Core GPUs that come with 80 ray tracing cores and 24 GB of memory per GPU.”
https://aws.amazon.com/ec2/instance-types/g5/ - T1 · upstream documentedofficial-docsverified 2026-10-24 (1d ago)
Hugging Face Jobs pricing lists A10G small/large flavors (24 GB).
“Nvidia A10G - small 4 vCPU 15 GB 24 GB 110 GB $1.00 Nvidia A10G - large 12 vCPU 46 GB 24 GB 200 GB $1.50”
https://huggingface.co/docs/hub/jobs-pricing