HyperAI
Command Palette
Search for a command to run...
What can this GPU run?
Choose a GPU setup to find the open models that fit, and deploy one as an API.
Verified models first, then by average benchmark score.
| # | Model | Precision | Max context |
|---|---|---|---|
| 1 | 2026.08 | FP8 | 256K |
| 2 | 2026.06 | FP16 | 256K |
| 3 | 2026.03 | FP16 | 256K |
| 4 | 2026.01 | FP16 | 198K |
| 5 | 2026.08 | FP16 | 256K |
| 6 | 2026.06 | FP16 | 240K |
| 7 | 2026.05 | FP8 | 128K |
| 8 | 2025.06 | FP16 | 128K |
| 9 | 2026.07 | FP16 | 128K |
| 10 | 2025.11 | FP16 | 125K |
| 11 | 2025.07 | FP16 | 64K |
| 12 | 2026.04 | NVFP4 | 256K |
| 13 | 2026.07 | FP16 | 256K |
| 14 | 2026.08 | FP16 | 488K |
Deployment verified on HyperAI
Fits usable VRAM with weights plus KV cache at 64K+ context, at the best precision.