Gemma-4-26B-A4B-It-Japanese-64e needs about 17.4 GB of memory at Q4_K_S (a 8.9 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 4 quants, from 7.4 GB (IQ4_XS) to 26.4 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 32.2 GB.
Gemma-4-26B-A4B-It-Japanese-64e is a 13.2B-parameter Gemma model in GGUF format, quantized by JMingo. Its trained context length is 256K tokens. The repository has 4 quant files, from 7.4 GB (IQ4_XS) to 26.4 GB (BF16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ4_XS | 7.4 GB | 16.0 GB | Too big | Get file → | |
| Q4_K_S | 8.9 GB | 17.4 GB | Too big | Get file → | |
| Q4_K_XL | 9.1 GB | 17.7 GB | Too big | Get file → | |
| BF16 | 26.4 GB | 35.0 GB | Too big | Get file → |
What GPU do you need for Gemma-4-26B-A4B-It-Japanese-64e?
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 IQ4_XS (7.4 GB file, about 16.0 GB in use).
- 24 GB VRAM: the best quant that fits is Q4_K_XL (9.1 GB file, about 17.7 GB in use).
- 32 GB VRAM: the best quant that fits is Q4_K_XL (9.1 GB file, about 17.7 GB in use).
- 48 GB VRAM: the best quant that fits is BF16 (26.4 GB file, about 35.0 GB in use).
Which Gemma-4-26B-A4B-It-Japanese-64e quant should you choose?
Q4_K_S (8.9 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.
If memory is tight, the smallest file is IQ4_XS at 7.4 GB, with the quality trade-offs that come with fewer bits. 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
Frequently asked questions about Gemma-4-26B-A4B-It-Japanese-64e
How much VRAM does Gemma-4-26B-A4B-It-Japanese-64e need?
About 17.4 GB at Q4_K_S with an 8K context window. That is the 8.9 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-4-26B-A4B-It-Japanese-64e on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 16.0 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Gemma-4-26B-A4B-It-Japanese-64e GGUF?
It depends on the quant: IQ4_XS is 7.4 GB, Q4_K_S is 8.9 GB, Q4_K_XL is 9.1 GB, BF16 is 26.4 GB.
What context length does Gemma-4-26B-A4B-It-Japanese-64e support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 8.1 GB at 8K and 32.2 GB at 32K.
Where can I download Gemma-4-26B-A4B-It-Japanese-64e GGUF?
The files are on Hugging Face in the JMingo/gemma-4-26B-A4B-it-Japanese-64e-v2-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-4-26B-A4B-It-Japanese-64e 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.