EZO2.5 Gemma 3 12b It Preview needs about 11.0 GB of memory at Q4_K_M (a 7.3 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 24 quants, from 2.9 GB (IQ1_S) to 12.5 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 12.9 GB.
EZO2.5 Gemma 3 12b It Preview – 11.8B parameter LLM with vision support
EZO2.5 Gemma 3 12b It Preview is a 11.8B parameter model built on the Gemma3 architecture. It supports vision tasks and was trained with a 131072 token context window. The model is released under the gemma license for research use.
Good at
- Japanese language tasks
- Vision‑enabled inference
- Long‑context generation
Limits
- No commercial license
- Requires research‑grade usage
- No explicit vision benchmark data
Best for
- Japanese MT and translation
- Image‑captioning in research
- Long‑form text generation
Who it’s for. Researchers and developers needing a Japanese‑focused, vision‑enabled LLM for experimental projects. The model is intended for academic or proof‑of‑concept use only.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 2.9 GB | 6.7 GB | Fits | Get file → | |
| IQ1_M | 3.2 GB | 6.9 GB | Fits | Get file → | |
| IQ2_XXS | 3.5 GB | 7.2 GB | Tight | Get file → | |
| IQ2_XS | 3.8 GB | 7.6 GB | Tight | Get file → | |
| IQ2_S | 4.0 GB | 7.7 GB | Tight | Get file → | |
| IQ2_M | 4.3 GB | 8.0 GB | Too big | Get file → | |
| Q2_K | 4.8 GB | 8.5 GB | Too big | Get file → | |
| IQ3_XXS | 4.8 GB | 8.5 GB | Too big | Get file → | |
| IQ3_XS | 5.2 GB | 8.9 GB | Too big | Get file → | |
| Q3_K_S | 5.5 GB | 9.2 GB | Too big | Get file → | |
| IQ3_S | 5.5 GB | 9.2 GB | Too big | Get file → | |
| IQ3_M | 5.7 GB | 9.4 GB | Too big | Get file → | |
| Q3_K_M | 6.0 GB | 9.7 GB | Too big | Get file → | |
| Q3_K_L | 6.5 GB | 10.2 GB | Too big | Get file → | |
| IQ4_XS | 6.6 GB | 10.3 GB | Too big | Get file → | |
| Q4_0 | 6.9 GB | 10.6 GB | Too big | Get file → | |
| IQ4_NL | 6.9 GB | 10.6 GB | Too big | Get file → | |
| Q4_K_S | 6.9 GB | 10.7 GB | Too big | Get file → | |
| Q4_K_M | 7.3 GB | 11.0 GB | Too big | Get file → | |
| Q5_0 | 8.2 GB | 12.0 GB | Too big | Get file → | |
| Q5_K_S | 8.2 GB | 12.0 GB | Too big | Get file → | |
| Q5_K_M | 8.4 GB | 12.2 GB | Too big | Get file → | |
| Q6_K | 9.7 GB | 13.4 GB | Too big | Get file → | |
| Q8_0 | 12.5 GB | 16.2 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (2.95 GB, 6.7 GB memory at 8 k context) or IQ1_M (3.16 GB, 6.9 GB). For 12 GB VRAM, Q2_K (4.77 GB, 8.5 GB) or Q3_K_M (6.01 GB, 9.7 GB) are suitable. Larger VRAM allows higher‑quality quants like Q4_K_M (7.3 GB, 11 GB).
What GPU do you need for EZO2.5 Gemma 3 12b It Preview?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: the best quant that fits is IQ2_M (4.3 GB file, about 8.0 GB in use).
- 12 GB VRAM: the best quant that fits is Q5_0 (8.2 GB file, about 12.0 GB in use).
- 16 GB VRAM: the best quant that fits is Q6_K (9.7 GB file, about 13.4 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (12.5 GB file, about 16.2 GB in use).
Which EZO2.5 Gemma 3 12b It Preview quant should you choose?
Q4_K_M is the usual starting point for EZO2.5 Gemma 3 12b It Preview: it balances file size and quality well. Here it is a 7.3 GB file.
The Q8_0 file is 12.5 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is IQ1_S at 2.9 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about EZO2.5 Gemma 3 12b It Preview
How much VRAM does EZO2.5 Gemma 3 12b It Preview need?
About 11.0 GB at Q4_K_M with an 8K context window. That is the 7.3 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run EZO2.5 Gemma 3 12b It Preview on an 8 GB GPU?
Yes, with IQ2_M: the 4.3 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of EZO2.5 Gemma 3 12b It Preview GGUF?
It depends on the quant: IQ1_S is 2.9 GB, IQ1_M is 3.2 GB, IQ2_XXS is 3.5 GB, IQ2_XS is 3.8 GB, IQ2_S is 4.0 GB, IQ2_M is 4.3 GB and 18 more.
What context length does EZO2.5 Gemma 3 12b It Preview support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 3.2 GB at 8K and 12.9 GB at 32K.
Where can I download EZO2.5 Gemma 3 12b It Preview GGUF?
The files are on Hugging Face in the mmnga/EZO2.5-gemma-3-12b-it-Preview-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does EZO2.5 Gemma 3 12b It Preview use?
Hugging Face lists the license as gemma. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run this model on 8 GB VRAM?
Yes, use IQ1_S or IQ1_M quantizations; they fit within 8 GB VRAM with estimated 6.7–6.9 GB usage at 8 k context.
Does the model support image input?
Yes, the model has vision capabilities as indicated in its detected abilities.
Is the model licensed for commercial use?
No, the gemma license restricts use to research purposes only.