Can I run gemma-4-12b-it-GGUF on an RTX 3060 12 GB?
Yes
Its UD-Q5_K_XL file (8.61 GB) fits in the 10.8 GB an RTX 3060 12 GB can use, with room for ≈ 11K tokens of context.
Full analysis of gemma-4-12b-it-GGUF
Everything that runs on RTX 3060 12 GB
Get the UD-Q5_K_XL file on Hugging Face
ollama run hf.co/unsloth/gemma-4-12b-it-GGUF:UD-Q5_K_XLFiles and context on RTX 3060 12 GB
Each file of gemma-4-12b-it-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) |
|---|---|---|---|---|
| gemma-4-12b-it-BF16 | 23.8 GB | Doesn't fit | — | — |
| UD-Q8_K_XL | 13.6 GB | Doesn't fit | — | — |
| gemma-4-12b-it-Q8_0 | 12.7 GB | Doesn't fit | — | — |
| UD-Q6_K_XL | 10.7 GB | Doesn't fit | 146 | 292 |
| Q6_K | 9.79 GB | Doesn't fit | 3K | 10K |
| UD-Q5_K_XL | 8.61 GB | Fits | 11K | 28K |
| Q5_K_M | 8.41 GB | Fits | 13K | 31K |
| Q5_K_S | 8.20 GB | Fits | 14K | 34K |
| Q4_1 | 7.40 GB | Fits | 20K | 46K |
| UD-Q4_K_XL | 7.37 GB | Fits | 21K | 46K |
| Q4_K_M | 7.12 GB | Fits | 22K | 50K |
| Q4_K_S | 6.76 GB | Fits | 25K | 55K |
| Q4_0 | 6.74 GB | Fits | 25K | 56K |
| IQ4_NL | 6.72 GB | Fits | 25K | 56K |
| IQ4_XS | 6.38 GB | Fits | 28K | 61K |
| UD-Q3_K_XL | 6.02 GB | Fits | 31K | 66K |
| Q3_K_M | 5.69 GB | Fits | 33K | 71K |
| Q3_K_S | 5.14 GB | Fits | 37K | 79K |
| UD-Q2_K_XL | 4.66 GB | Fits | 41K | 86K |
| UD-IQ3_XXS | 4.64 GB | Fits | 41K | 87K |
| UD-IQ2_M | 4.21 GB | Fits | 44K | 93K |