gemma-4-12B-it needs about 21.1 GB of memory at Q4_K_M (a 7.7 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 29 quants, from 0.0 GB to 23.8 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 51.5 GB.
Gemma 4 12B instruction tuned model with 256K token context
Gemma 4 12B‑it is an instruction‑tuned variant of the Gemma 4 family. It supports text and image input with a 256K token context window. The model is released under Apache‑2.0 and is available in multiple GGUF quantizations.
Good at
- Large context handling
- Instruction following
- Multimodal text‑image tasks
Limits
- No vision encoder required but no native vision support in this variant
- Requires 256K context for full capability
- License is Apache‑2.0
Best for
- Chatbots needing long context
- Content generation with image prompts
- Local deployment on laptops
Who it’s for. Developers building local LLM applications that need a large context window and instruction‑tuned behavior. The model is suitable for on‑device inference on laptops and servers.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 13.4 GB | Too big | Get file → | |
| Q1_0 | 2.7 GB | 16.1 GB | Too big | Get file → | |
| IQ1_S | 2.9 GB | 16.3 GB | Too big | Get file → | |
| IQ1_M | 3.4 GB | 16.8 GB | Too big | Get file → | |
| IQ2_XXS | 3.6 GB | 17.0 GB | Too big | Get file → | |
| IQ2_XS | 4.0 GB | 17.3 GB | Too big | Get file → | |
| IQ2_S | 4.2 GB | 17.6 GB | Too big | Get file → | |
| IQ2_M | 4.5 GB | 17.8 GB | Too big | Get file → | |
| Q2_K_S | 4.7 GB | 18.1 GB | Too big | Get file → | |
| Q2_K_M | 4.9 GB | 18.3 GB | Too big | Get file → | |
| IQ3_XXS | 5.0 GB | 18.4 GB | Too big | Get file → | |
| IQ3_XS | 5.3 GB | 18.7 GB | Too big | Get file → | |
| IQ3_M | 5.8 GB | 19.2 GB | Too big | Get file → | |
| Q3_K_S | 6.1 GB | 19.5 GB | Too big | Get file → | |
| Q3_K_M | 6.3 GB | 19.7 GB | Too big | Get file → | |
| IQ4_XS | 6.6 GB | 20.0 GB | Too big | Get file → | |
| IQ4_NL | 6.7 GB | 20.1 GB | Too big | Get file → | |
| Q4_0 | 7.2 GB | 20.6 GB | Too big | Get file → | |
| Q4_K_S | 7.3 GB | 20.7 GB | Too big | Get file → | |
| Q4_1 | 7.5 GB | 20.9 GB | Too big | Get file → | |
| Q4_K_M | 7.7 GB | 21.1 GB | Too big | Get file → | |
| Q5_0 | 8.6 GB | 22.0 GB | Too big | Get file → | |
| Q5_K_M | 9.0 GB | 22.4 GB | Too big | Get file → | |
| Q5_1 | 9.3 GB | 22.6 GB | Too big | Get file → | |
| Q6_K_M | 10.0 GB | 23.4 GB | Too big | Get file → | |
| Q8_0 | 12.7 GB | 26.1 GB | Too big | Get file → | |
| BF16 | 17.4 GB | 30.8 GB | Too big | Get file → | |
| F16 | 17.4 GB | 30.8 GB | Too big | Get file → | |
| BF16 | 23.8 GB | 37.2 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (7.74 GB file, 21.1 GB memory at 8K context). For 16 GB VRAM, Q5_K_M (8.99 GB file, 22.4 GB memory) or Q6_K_M (10.03 GB file, 23.4 GB memory). Higher precision models like BF16 need 30.8 GB memory and are best on larger GPUs.
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 the main file (0.0 GB file, about 13.4 GB in use).
- 24 GB VRAM: the best quant that fits is Q6_K_M (10.0 GB file, about 23.4 GB in use).
- 32 GB VRAM: the best quant that fits is BF16 (17.4 GB file, about 30.8 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 7.7 GB file.
The Q8_0 file is 12.7 GB, about 1.6 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 the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.
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 21.1 GB at Q4_K_M with an 8K context window. That is the 7.7 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-it on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 13.4 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: file is 0.0 GB, Q1_0 is 2.7 GB, IQ1_S is 2.9 GB, IQ1_M is 3.4 GB, IQ2_XXS is 3.6 GB, IQ2_XS is 4.0 GB and 23 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 Mungert/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 a Q4_K_M quantized file; it requires about 21.1 GB memory at 8K context, which exceeds 8 GB VRAM. A smaller quant like Q4_K_S (20.7 GB) is also too large for 8 GB VRAM.
Does this model support image input?
Yes, the model handles text and image input, but it does not include a separate vision encoder.
What license applies to this model?
The model is released under the Apache‑2.0 license.