gemma-4-12B needs about 26.1 GB of memory at Q8_0 (a 12.7 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 2 quants, from 12.7 GB (Q8_0) to 23.8 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 51.5 GB.
Gemma 4 12B – 11.9B parameter multimodal LLM
Gemma 4 12B is a 11.9B parameter model that supports text, image, audio, and video inputs. It offers a 256K token context window and native function‑calling. The model is open‑weight and licensed under Apache‑2.0.
Good at
- Text generation
- Coding assistance
- Reasoning tasks
Limits
- Requires 26.1GB VRAM for Q8_0 at 8k context
- No separate vision encoders needed
- Apache‑2.0 license
Best for
- Local text generation
- Coding support
- Complex reasoning
Who it’s for. Developers and researchers who need a local, multimodal LLM with a large context window and native function‑calling. The model runs on consumer devices with sufficient VRAM.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 12.7 GB | 26.1 GB | Too big | Get file → | |
| BF16 | 23.8 GB | 37.2 GB | Too big | Get file → |
For 8‑GB VRAM, Q8_0 is the smallest file at 12.67 GB, but it still needs about 26.1 GB of VRAM at 8k context. BF16 is larger at 23.83 GB and requires about 37.2 GB of VRAM. Choose the quant that fits your memory budget.
What GPU do you need for gemma-4-12B?
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: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: no quant fits at an 8K context.
- 32 GB VRAM: the best quant that fits is Q8_0 (12.7 GB file, about 26.1 GB in use).
- 48 GB VRAM: the best quant that fits is BF16 (23.8 GB file, about 37.2 GB in use).
Which gemma-4-12B quant should you choose?
Q8_0 (12.7 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about gemma-4-12B
How much VRAM does gemma-4-12B need?
About 26.1 GB at Q8_0 with an 8K context window. That is the 12.7 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-4-12B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 26.1 GB, so you would need a larger GPU or CPU offloading.
What is the file size of gemma-4-12B GGUF?
It depends on the quant: Q8_0 is 12.7 GB, BF16 is 23.8 GB.
What context length does gemma-4-12B support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 12.9 GB at 8K and 51.5 GB at 32K.
Where can I download gemma-4-12B GGUF?
The files are on Hugging Face in the ggml-org/gemma-4-12B-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-4-12B use?
Hugging Face lists the license as apache-2.0. 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 4 12B on 8 GB VRAM?
No. The smallest quant requires 26.1 GB of VRAM at 8k context. You need at least 26 GB VRAM to run it.
Does this model support vision?
Yes. Gemma 4 12B handles image, audio, and video inputs without separate encoders.
What license does it use?
Apache‑2.0. The weights are open‑source and can be used freely.