Can I run Raon-1-mini-preview on an RTX 3060 12 GB?
No
Even its smallest file (4-bit (estimate), 16.2 GB) is more than an RTX 3060 12 GB can hold (10.8 GB usable): it needs 2 of them.
Files and context on RTX 3060 12 GB
Each file of Raon-1-mini-preview (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 3060 12 GB | Context (16-bit) | Context (8-bit) |
|---|---|---|---|---|
| As published | 32.7 GB | Doesn't fit | — | — |
| raon-1-mini-preview-Q8_0 | 30.7 GB | Doesn't fit | — | — |
| Q6_K | 25.8 GB | Doesn't fit | — | — |
| Q5_K_M | 22.2 GB | Doesn't fit | — | — |
| Q4_K_M | 19.7 GB | Doesn't fit | — | — |
| IQ4_XS | 16.1 GB | Doesn't fit | — | — |