Can I run Dirk-Qwen3.8-27B-GGUF on an RTX 4060?
No
Even its smallest file (IQ2_XS, 8.77 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 Dirk-Qwen3.8-27B-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) |
|---|---|---|---|---|
| UD-Q8_K_XL | 31.5 GB | Doesn't fit | — | — |
| UD-Q8_K_L | 28.0 GB | Doesn't fit | — | — |
| UD-Q6_K_XL | 25.3 GB | Doesn't fit | — | — |
| UD-Q6_K | 22.0 GB | Doesn't fit | — | — |
| UD-Q5_K_XL | 20.9 GB | Doesn't fit | — | — |
| UD-Q4_K_XL | 17.6 GB | Doesn't fit | — | — |
| UD-Q4_K_S | 15.4 GB | Doesn't fit | — | — |
| UD-IQ4_XS | 14.3 GB | Doesn't fit | — | — |
| UD-Q3_K_XL | 13.1 GB | Doesn't fit | — | — |
| IQ3_S | 12.1 GB | Doesn't fit | — | — |
| IQ3_XXS | 10.4 GB | Doesn't fit | — | — |
| UD-Q2_K_XL | 9.83 GB | Doesn't fit | — | — |
| IQ2_S | 9.61 GB | Doesn't fit | — | — |
| IQ2_XS | 8.77 GB | Doesn't fit | — | — |