Gemma-4-12B-It needs about 20.5 GB of memory at Q4_K_M (a 7.1 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 25 quants, from 0.5 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‑It: 12B multimodal instruction‑tuned model
Gemma‑4‑12B‑It is a 12B parameter model that supports text, image, audio, and video inputs. It offers a 256K token context window and is released under Apache 2.0. The model is encoder‑free and designed for local deployment.
Good at
- Multimodal text and image generation
- Instruction following
- Large context handling
Limits
- No vision support in some quantizations
- Large VRAM needed for high‑precision quants
- Requires Apache 2.0 license compliance
Best for
- Local multimodal chatbots
- On‑device content creation
- Research prototyping
Who it’s for. Developers and researchers who need a local, multimodal LLM with instruction tuning. The model is suitable for laptops and servers that can accommodate its memory footprint.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 0.5 GB | 13.9 GB | Too big | Get file → | |
| — | 0.5 GB | 13.9 GB | Too big | Get file → | |
| BF16 | 0.9 GB | 14.2 GB | Too big | Get file → | |
| F16 | 0.9 GB | 14.2 GB | Too big | Get file → | |
| IQ2_M | 4.2 GB | 17.6 GB | Too big | Get file → | |
| IQ3_XXS | 4.6 GB | 18.0 GB | Too big | Get file → | |
| Q2_K_XL | 4.7 GB | 18.0 GB | Too big | Get file → | |
| Q3_K_S | 5.1 GB | 18.5 GB | Too big | Get file → | |
| Q3_K_M | 5.7 GB | 19.1 GB | Too big | Get file → | |
| Q3_K_XL | 6.0 GB | 19.4 GB | Too big | Get file → | |
| IQ4_XS | 6.4 GB | 19.8 GB | Too big | Get file → | |
| IQ4_NL | 6.7 GB | 20.1 GB | Too big | Get file → | |
| Q4_0 | 6.7 GB | 20.1 GB | Too big | Get file → | |
| Q4_K_S | 6.8 GB | 20.1 GB | Too big | Get file → | |
| Q4_K_M | 7.1 GB | 20.5 GB | Too big | Get file → | |
| Q4_K_XL | 7.4 GB | 20.8 GB | Too big | Get file → | |
| Q4_1 | 7.4 GB | 20.8 GB | Too big | Get file → | |
| Q5_K_S | 8.2 GB | 21.6 GB | Too big | Get file → | |
| Q5_K_M | 8.4 GB | 21.8 GB | Too big | Get file → | |
| Q5_K_XL | 8.6 GB | 22.0 GB | Too big | Get file → | |
| Q6_K | 9.8 GB | 23.2 GB | Too big | Get file → | |
| Q6_K_XL | 10.7 GB | 24.1 GB | Too big | Get file → | |
| Q8_0 | 12.7 GB | 26.1 GB | Too big | Get file → | |
| Q8_K_XL | 13.6 GB | 27.0 GB | Too big | Get file → | |
| BF16 | 23.8 GB | 37.2 GB | Too big | Get file → |
For 8 GB VRAM use Q4_K_M (file size 7.12 GB, ~20.5 GB memory). For 12 GB VRAM use Q4_K_XL (file size 7.37 GB, ~20.8 GB memory). For 16 GB VRAM use Q5_K_M (file size 8.41 GB, ~21.8 GB memory).
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: the best quant that fits is BF16 (0.9 GB file, about 14.2 GB in use).
- 24 GB VRAM: the best quant that fits is Q6_K (9.8 GB file, about 23.2 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_K_XL (13.6 GB file, about 27.0 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-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 7.1 GB file.
The Q8_0 file is 0.5 GB, about 0.1 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 Q8_0 at 0.5 GB, with the quality trade-offs that come with fewer bits. 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-It
How much VRAM does Gemma-4-12B-It need?
About 20.5 GB at Q4_K_M with an 8K context window. That is the 7.1 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 13.9 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: Q8_0 is 0.5 GB, file is 0.5 GB, BF16 is 0.9 GB, F16 is 0.9 GB, IQ2_M is 4.2 GB, IQ3_XXS is 4.6 GB and 19 more.
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 sebidev/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?
Use the Q4_K_M quantization; it requires about 20.5 GB VRAM at 8k context, which is beyond 8 GB. Lower quants are not available for this model.
Does the model support vision?
Yes, the model has detected vision ability and supports image inputs natively.
What license does the model use?
The model is released under the Apache 2.0 license.