Can I run inkling-GGUF on an RTX 3060 12 GB?
No
Even its smallest file (UD-IQ1_S, 270 GB) is more than an RTX 3060 12 GB can hold (10.8 GB usable): it needs more than 8 of them.
Files and context on RTX 3060 12 GB
Each file of inkling-GGUF (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) |
|---|---|---|---|---|
| BF16 | 1.89 TB | Doesn't fit | — | — |
| Q8_0 | 857 GB | Doesn't fit | — | — |
| UD-Q4_K_XL | 587 GB | Doesn't fit | — | — |
| UD-Q3_K_XL | 433 GB | Doesn't fit | — | — |
| UD-Q2_K_XL | 317 GB | Doesn't fit | — | — |
| UD-IQ1_M | 285 GB | Doesn't fit | — | — |
| UD-IQ1_S | 270 GB | Doesn't fit | — | — |