Gemma 3 12b needs about 10.6 GB of memory at Q4_0 (a 6.9 GB file) with an 8K context window, so it fits on a 12 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 12.9 GB.
Gemma 3 12b – 12B multimodal LLM with 128k context
Gemma 3 12b is a 12‑billion parameter multimodal model supporting text and image inputs. It offers a 128k token context length and 8192 token maximum output. The model is optimized with Quantization Aware Training for efficient 4‑bit inference.
Good at
- Text generation
- Image understanding
- Question answering
Limits
- No vision support beyond 896x896 images
- Requires 128k context for full capability
- License is gemma
Best for
- Chatbots needing large context
- Summarization of long documents
- Multimodal reasoning tasks
Who it’s for. Developers building multimodal applications that require a large context window and efficient inference. Ideal for teams using llama.cpp and GGUF formats.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_0 | 6.9 GB | 10.6 GB | Too big | Get file → |
The Q4_0 quant file is 6.89 GB and needs about 10.6 GB of VRAM at 8k context. For 8 GB VRAM, use a lower‑precision quant if available. For 16 GB VRAM, Q4_0 is suitable.
What GPU do you need for Gemma 3 12b?
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_0 (6.9 GB file, about 10.6 GB in use).
Which Gemma 3 12b quant should you choose?
Q4_0 (6.9 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Gemma 3 12b
How much VRAM does Gemma 3 12b need?
About 10.6 GB at Q4_0 with an 8K context window. That is the 6.9 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 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 10.6 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Gemma 3 12b GGUF?
It depends on the quant: Q4_0 is 6.9 GB.
What context length does Gemma 3 12b 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 GGUF?
The files are on Hugging Face in the lmstudio-community/gemma-3-12B-it-qat-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 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 Gemma 3 12b on 8 GB VRAM?
The Q4_0 quant requires about 10.6 GB VRAM at 8k context, so 8 GB VRAM is insufficient.
What is the maximum output length?
The model supports a maximum output of 8192 tokens.
Does it support image inputs?
Yes, it supports images normalized to 896 × 896 resolution.