Can I run Ornith-1.5-122B-GGUF on an RTX 3090?
No
Even its smallest file (UD-IQ1_M, 40.4 GB) is more than an RTX 3090 can hold (21.6 GB usable): it needs 2 of them.
Files and context on RTX 3090
Each file of Ornith-1.5-122B-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 3090 | Context (16-bit) | Context (8-bit) |
|---|---|---|---|---|
| BF16 | 249 GB | Doesn't fit | — | — |
| Q8_0 | 133 GB | Doesn't fit | — | — |
| UD-Q6_K_XL | 114 GB | Doesn't fit | — | — |
| UD-Q5_K_XL | 94.6 GB | Doesn't fit | — | — |
| UD-Q4_K_XL | 79.7 GB | Doesn't fit | — | — |
| UD-Q3_K_XL | 59.8 GB | Doesn't fit | — | — |
| UD-IQ3_XXS | 49.5 GB | Doesn't fit | — | — |
| UD-Q2_K_XL | 44.5 GB | Doesn't fit | — | — |
| UD-IQ2_XXS | 42.0 GB | Doesn't fit | — | — |
| UD-IQ1_M | 40.4 GB | Doesn't fit | — | — |