Can I run XYZAILab_XYZ-Aquila-mini-GGUF on an RTX 3060 12 GB?
Yes, just
Its IQ2_XXS file (9.78 GB) fits in the 10.8 GB an RTX 3060 12 GB can use, with room for ≈ 46K tokens of context. That file is under 3 bits per weight, so expect noticeably lower quality.
Full analysis of XYZAILab_XYZ-Aquila-mini-GGUF
Everything that runs on RTX 3060 12 GB
Get the IQ2_XXS file on Hugging Face
ollama run hf.co/bartowski/XYZAILab_XYZ-Aquila-mini-GGUF:IQ2_XXSFiles and context on RTX 3060 12 GB
Each file of XYZAILab_XYZ-Aquila-mini-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) |
|---|---|---|---|---|
| BF16 | 69.4 GB | Doesn't fit | — | — |
| Q8_0 | 36.9 GB | Doesn't fit | — | — |
| Q6_K_L | 30.3 GB | Doesn't fit | — | — |
| Q6_K | 30.1 GB | Doesn't fit | — | — |
| Q5_K_L | 25.3 GB | Doesn't fit | — | — |
| Q5_K_M | 25.0 GB | Doesn't fit | — | — |
| Q5_K_S | 24.2 GB | Doesn't fit | — | — |
| Q4_1 | 22.0 GB | Doesn't fit | — | — |
| Q4_K_L | 21.8 GB | Doesn't fit | — | — |
| Q4_K_M | 21.4 GB | Doesn't fit | — | — |
| Q4_K_S | 20.6 GB | Doesn't fit | — | — |
| Q4_0 | 19.9 GB | Doesn't fit | — | — |
| IQ4_NL | 19.9 GB | Doesn't fit | — | — |
| IQ4_XS | 18.8 GB | Doesn't fit | — | — |
| Q3_K_XL | 17.3 GB | Doesn't fit | — | — |
| IQ3_M | 16.9 GB | Doesn't fit | — | — |
| Q3_K_L | 16.9 GB | Doesn't fit | — | — |
| Q3_K_M | 16.2 GB | Doesn't fit | — | — |
| IQ3_XS | 16.2 GB | Doesn't fit | — | — |
| Q3_K_S | 15.5 GB | Doesn't fit | — | — |
| IQ3_XXS | 14.9 GB | Doesn't fit | — | — |
| Q2_K_L | 13.1 GB | Doesn't fit | — | — |
| Q2_K | 12.6 GB | Doesn't fit | — | — |
| IQ2_M | 12.1 GB | Doesn't fit | — | — |
| IQ2_S | 11.0 GB | Doesn't fit | — | — |
| IQ2_XS | 10.8 GB | Doesn't fit | — | — |
| IQ2_XXS | 9.78 GB | Tight | 46K | 91K |