Can I run endless-frontier_BigBang-v1-GGUF on an RTX 4060?
No
Even its smallest file (IQ2_XXS, 10.3 GB) is more than an RTX 4060 can hold (7.20 GB usable): it needs 2 of them.
Files and context on RTX 4060
Each file of endless-frontier_BigBang-v1-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 4060 | Context (16-bit) | Context (8-bit) |
|---|---|---|---|---|
| BF16 | 71.1 GB | Doesn't fit | — | — |
| Q8_0 | 37.8 GB | Doesn't fit | — | — |
| Q6_K_L | 30.8 GB | Doesn't fit | — | — |
| Q6_K | 30.5 GB | Doesn't fit | — | — |
| Q5_K_L | 25.8 GB | Doesn't fit | — | — |
| Q5_K_M | 25.5 GB | Doesn't fit | — | — |
| Q5_K_S | 24.6 GB | Doesn't fit | — | — |
| Q4_1 | 22.4 GB | Doesn't fit | — | — |
| Q4_K_L | 22.2 GB | Doesn't fit | — | — |
| Q4_K_M | 21.9 GB | Doesn't fit | — | — |
| Q4_K_S | 21.1 GB | Doesn't fit | — | — |
| Q4_0 | 20.4 GB | Doesn't fit | — | — |
| IQ4_NL | 20.3 GB | Doesn't fit | — | — |
| IQ4_XS | 19.3 GB | Doesn't fit | — | — |
| Q3_K_XL | 17.8 GB | Doesn't fit | — | — |
| IQ3_M | 17.4 GB | Doesn't fit | — | — |
| Q3_K_L | 17.4 GB | Doesn't fit | — | — |
| Q3_K_M | 16.7 GB | Doesn't fit | — | — |
| IQ3_XS | 16.7 GB | Doesn't fit | — | — |
| Q3_K_S | 16.0 GB | Doesn't fit | — | — |
| IQ3_XXS | 15.3 GB | Doesn't fit | — | — |
| Q2_K_L | 13.6 GB | Doesn't fit | — | — |
| Q2_K | 13.1 GB | Doesn't fit | — | — |
| IQ2_M | 12.5 GB | Doesn't fit | — | — |
| IQ2_S | 11.5 GB | Doesn't fit | — | — |
| IQ2_XS | 11.3 GB | Doesn't fit | — | — |
| IQ2_XXS | 10.3 GB | Doesn't fit | — | — |