Can I run Hy3 on an RTX 5090?
No
Even its smallest file (4-bit (estimate), 168 GB) is more than an RTX 5090 can hold (28.8 GB usable): it needs 6 of them.
Files and context on RTX 5090
Each file of Hy3 (and of GGUF versions the site has analyzed), and how much context fits next to it, with the context cache in 16-bit or 8-bit.
| File | Size | On RTX 5090 | Context (16-bit) | Context (8-bit) |
|---|---|---|---|---|
| As published | 598 GB | Doesn't fit | — | — |
| 4-bit (estimate) | 168 GB | Doesn't fit | — | — |