Gemma-3-12B-It-Qat-Int4 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 18 quants, from 4.4 GB (IQ1_S) to 23.5 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 12.9 GB.
Gemma‑3‑12B‑It‑Qat‑Int4 – 12B instruction‑tuned multimodal model
Gemma‑3‑12B‑It‑Qat‑Int4 is a 12B parameter instruction‑tuned model from the Gemma family. It supports text and image input with a 128K token context window. The model is quantized using QAT to preserve quality while reducing memory usage.
Good at
- Multimodal text and image tasks
- Large 128K context
- Instruction‑tuned responses
Limits
- No vision support beyond 896x896 images
- Requires 8K context for memory estimates
- License is gemma
Best for
- Chatbots needing large context
- Image‑to‑text summarization
- Multilingual Q&A
Who it’s for. Developers building lightweight multimodal applications on laptops or small servers. The model is suitable for those who need a balance between performance and memory footprint.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 4.4 GB | 8.1 GB | Too big | Get file → | |
| IQ1_M | 4.5 GB | 8.3 GB | Too big | Get file → | |
| Q2_K | 4.8 GB | 8.5 GB | Too big | Get file → | |
| IQ2_XXS | 5.0 GB | 8.7 GB | Too big | Get file → | |
| IQ2_M | 5.1 GB | 8.8 GB | Too big | Get file → | |
| Q2_K_L | 6.0 GB | 9.7 GB | Too big | Get file → | |
| Q3_K_M | 6.0 GB | 9.7 GB | Too big | Get file → | |
| IQ3_XXS | 6.1 GB | 9.9 GB | Too big | Get file → | |
| Q2_K_XL | 6.3 GB | 10.1 GB | Too big | Get file → | |
| IQ4_XS | 6.6 GB | 10.3 GB | Too big | Get file → | |
| Q3_K_XL | 7.3 GB | 11.0 GB | Too big | Get file → | |
| Q4_K_M | 7.3 GB | 11.0 GB | Too big | Get file → | |
| Q4_0 | 8.1 GB | 11.8 GB | Too big | Get file → | |
| Q4_K_XL | 8.1 GB | 11.8 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 → | |
| BF16 | 23.5 GB | 27.3 GB | Too big | Get file → |
For 8–10 GB VRAM, use Q4_K_M (file size 7.3 GB, ~11 GB memory). For 12–14 GB VRAM, Q5_K_M (8.45 GB, ~12.2 GB memory) or Q6_K (9.66 GB, ~13.4 GB memory). For 16 GB VRAM, Q8_0 (12.51 GB, ~16.2 GB memory).
What GPU do you need for Gemma-3-12B-It-Qat-Int4?
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: no quant fits at an 8K context.
- 12 GB VRAM: the best quant that fits is Q4_K_XL (8.1 GB file, about 11.8 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).
- 32 GB VRAM: the best quant that fits is BF16 (23.5 GB file, about 27.3 GB in use).
Which Gemma-3-12B-It-Qat-Int4 quant should you choose?
Q4_K_M is the usual starting point for Gemma-3-12B-It-Qat-Int4: 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 4.4 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 Gemma-3-12B-It-Qat-Int4
How much VRAM does Gemma-3-12B-It-Qat-Int4 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 Gemma-3-12B-It-Qat-Int4 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 8.1 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Gemma-3-12B-It-Qat-Int4 GGUF?
It depends on the quant: IQ1_S is 4.4 GB, IQ1_M is 4.5 GB, Q2_K is 4.8 GB, IQ2_XXS is 5.0 GB, IQ2_M is 5.1 GB, Q2_K_L is 6.0 GB and 12 more.
What context length does Gemma-3-12B-It-Qat-Int4 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 Gemma-3-12B-It-Qat-Int4 GGUF?
The files are on Hugging Face in the unsloth/gemma-3-12b-it-qat-int4-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 Gemma-3-12B-It-Qat-Int4 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, using Q4_K_M or Q4_K_XL will fit within 8–10 GB VRAM with the estimated memory usage.
Does the model support image input?
Yes, it accepts images normalized to 896×896 resolution, encoded to 256 tokens each.
What is the context window size?
The model supports a 128K token context window for all sizes.