Gemma 4 12B It needs about 20.8 GB of memory at Q4_K_M (a 7.4 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 2 quants, from 7.4 GB (Q4_K_M) to 12.7 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 51.5 GB.
Gemma 4 12B It – multimodal instruction‑tuned model with 256K context
Gemma 4 12B It is a 11.9B‑parameter model that supports text, image, audio, and video inputs. It offers a 256K token context window and native system prompt support. The model is released under Apache‑2.0 and is available in GGUF format for llama.cpp.
Good at
- Multimodal inference with image and audio
- Large context handling up to 256K tokens
- Instruction‑tuned text generation
Limits
- Requires 20.8 GB VRAM for Q4_K_M at 8K context
- No reliable audio transcription with current llama.cpp
- License is Apache‑2.0
Best for
- Local chat applications with image input
- Multimodal research on consumer devices
- Developing autonomous agents with native function‑calling
Who it’s for. Developers and researchers who need a multimodal LLM that can run locally on laptops or mobile devices. The model is suitable for building chatbots, coding assistants, and agents that handle text, image, audio, and video.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 7.4 GB | 20.8 GB | Too big | Get file → | |
| Q8_0 | 12.7 GB | 26.1 GB | Too big | Get file → |
For 8 GB VRAM use Q4_K_M (7.38 GB file, ~20.8 GB memory at 8K context). For 12 GB VRAM use Q8_0 (12.67 GB file, ~26.1 GB memory at 8K context). Memory estimates are approximate.
What GPU do you need for Gemma 4 12B It?
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: the best quant that fits is Q4_K_M (7.4 GB file, about 20.8 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (12.7 GB file, about 26.1 GB in use).
Which Gemma 4 12B It quant should you choose?
Q4_K_M is the usual starting point for Gemma 4 12B It: it balances file size and quality well. Here it is a 7.4 GB file.
The Q8_0 file is 12.7 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Gemma 4 12B It
How much VRAM does Gemma 4 12B It need?
About 20.8 GB at Q4_K_M with an 8K context window. That is the 7.4 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 It on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 20.8 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Gemma 4 12B It GGUF?
It depends on the quant: Q4_K_M is 7.4 GB, Q8_0 is 12.7 GB.
What context length does Gemma 4 12B It 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 It GGUF?
The files are on Hugging Face in the SoAIHQ/gemma-4-12B-it-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 It 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 It on 8 GB VRAM?
No, the Q4_K_M quant requires about 20.8 GB memory at 8K context, which exceeds 8 GB VRAM.
Does the model support audio input?
Audio is supported natively on the 12B variant, but current llama.cpp versions do not reliably transcribe audio yet.
What license applies to this model?
The model is released under the Apache‑2.0 license.