Can I run gemma-4-26B-A4B-it on an RTX 5060 Ti 16 GB?
Yes, with a GGUF version
The published weights are too big, but the UD-IQ4_NL file from unsloth/gemma-4-26B-A4B-it-GGUF (13.6 GB) fits, with room for ≈ 4K tokens of context.
Full analysis of gemma-4-26B-A4B-it
Everything that runs on RTX 5060 Ti 16 GB
Get the UD-IQ4_NL file on Hugging Face
ollama run hf.co/unsloth/gemma-4-26B-A4B-it-GGUF:UD-IQ4_NLFiles and context on RTX 5060 Ti 16 GB
Each file of gemma-4-26B-A4B-it (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) |
|---|---|---|---|---|
| As published | 51.6 GB | Doesn't fit | — | — |
| BF16 | 50.5 GB | Doesn't fit | — | — |
| UD-Q8_K_XL | 27.6 GB | Doesn't fit | — | — |
| Q8_0 | 26.9 GB | Doesn't fit | — | — |
| UD-Q6_K_XL | 23.3 GB | Doesn't fit | — | — |
| UD-Q6_K | 23.2 GB | Doesn't fit | — | — |
| UD-Q5_K_XL | 21.2 GB | Doesn't fit | — | — |
| UD-Q5_K_M | 21.2 GB | Doesn't fit | — | — |
| UD-Q5_K_S | 18.9 GB | Doesn't fit | — | — |
| UD-Q4_K_XL | 17.0 GB | Doesn't fit | — | — |
| UD-Q4_K_M | 16.9 GB | Doesn't fit | — | — |
| MXFP4_MOE | 16.6 GB | Doesn't fit | — | — |
| UD-Q4_K_S | 16.5 GB | Doesn't fit | — | — |
| UD-IQ4_NL | 13.6 GB | Tight | 4K | 14K |
| UD-IQ4_XS | 13.6 GB | Tight | 5K | 14K |
| UD-Q3_K_XL | 12.9 GB | Tight | 13K | 31K |
| UD-Q3_K_M | 12.7 GB | Tight | 15K | 35K |
| UD-IQ3_XXS | 11.4 GB | Fits | 31K | 66K |
| UD-IQ3_S | 11.3 GB | Fits | 32K | 69K |
| UD-Q2_K_XL | 10.5 GB | Fits | 41K | 87K |
| UD-IQ2_M | 10.0 GB | Fits | 47K | 100K |
| UD-IQ2_XXS | 9.92 GB | Fits | 48K | 102K |