Can I run gemma-4-12b-it-GGUF on an RTX 4060?
Yes
Its Q3_K_M file (5.69 GB) fits in the 7.20 GB an RTX 4060 can use, with room for ≈ 6K tokens of context.
Full analysis of gemma-4-12b-it-GGUF
Everything that runs on RTX 4060
Get the Q3_K_M file on Hugging Face
ollama run hf.co/unsloth/gemma-4-12b-it-GGUF:Q3_K_MFiles and context on RTX 4060
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 4060 | 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 | — | — |
| Q6_K | 9.79 GB | Doesn't fit | — | — |
| UD-Q5_K_XL | 8.61 GB | Doesn't fit | — | — |
| Q5_K_M | 8.41 GB | Doesn't fit | — | — |
| Q5_K_S | 8.20 GB | Doesn't fit | — | — |
| Q4_1 | 7.40 GB | Doesn't fit | — | — |
| UD-Q4_K_XL | 7.37 GB | Doesn't fit | — | — |
| Q4_K_M | 7.12 GB | Doesn't fit | 99 | 198 |
| Q4_K_S | 6.76 GB | Doesn't fit | 553 | 1K |
| Q4_0 | 6.74 GB | Doesn't fit | 586 | 2K |
| IQ4_NL | 6.72 GB | Doesn't fit | 614 | 2K |
| IQ4_XS | 6.38 GB | Doesn't fit | 1K | 7K |
| UD-Q3_K_XL | 6.02 GB | Doesn't fit | 4K | 13K |
| Q3_K_M | 5.69 GB | Fits | 6K | 17K |
| Q3_K_S | 5.14 GB | Fits | 10K | 26K |
| UD-Q2_K_XL | 4.66 GB | Fits | 14K | 33K |
| UD-IQ3_XXS | 4.64 GB | Fits | 14K | 33K |
| UD-IQ2_M | 4.21 GB | Fits | 17K | 40K |