Can I run gemma-4-12b-it-GGUF on an RTX 5060 Ti 16 GB?
Yes, just
Its gemma-4-12b-it-Q8_0 file (12.7 GB) fits in the 14.4 GB an RTX 5060 Ti 16 GB can use, with room for ≈ 8K tokens of context.
Full analysis of gemma-4-12b-it-GGUF
Everything that runs on RTX 5060 Ti 16 GB
Get the gemma-4-12b-it-Q8_0 file on Hugging Face
ollama run hf.co/unsloth/gemma-4-12b-it-GGUFFiles and context on RTX 5060 Ti 16 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 5060 Ti 16 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 | 969 | 6K |
| gemma-4-12b-it-Q8_0 | 12.7 GB | Tight | 8K | 21K |
| UD-Q6_K_XL | 10.7 GB | Fits | 23K | 50K |
| Q6_K | 9.79 GB | Fits | 29K | 64K |
| UD-Q5_K_XL | 8.61 GB | Fits | 38K | 81K |
| Q5_K_M | 8.41 GB | Fits | 40K | 84K |
| Q5_K_S | 8.20 GB | Fits | 41K | 87K |
| Q4_1 | 7.40 GB | Fits | 47K | 99K |
| UD-Q4_K_XL | 7.37 GB | Fits | 47K | 100K |
| Q4_K_M | 7.12 GB | Fits | 49K | 103K |
| Q4_K_S | 6.76 GB | Fits | 52K | 109K |
| Q4_0 | 6.74 GB | Fits | 52K | 109K |
| IQ4_NL | 6.72 GB | Fits | 52K | 109K |
| IQ4_XS | 6.38 GB | Fits | 55K | 115K |
| UD-Q3_K_XL | 6.02 GB | Fits | 57K | 120K |
| Q3_K_M | 5.69 GB | Fits | 60K | 125K |
| Q3_K_S | 5.14 GB | Fits | 64K | 133K |
| UD-Q2_K_XL | 4.66 GB | Fits | 68K | 140K |
| UD-IQ3_XXS | 4.64 GB | Fits | 68K | 140K |
| UD-IQ2_M | 4.21 GB | Fits | 71K | 147K |