Gemma 4 26B A4B TAIDE zhTW needs about 25.3 GB of memory at Q4_K_M (a 16.8 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 6 quants, from 10.4 GB (IQ2_M) to 26.9 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 32.2 GB.
Gemma 4 26B A4B TAIDE zhTW – 26B parameter, multimodal, Traditional Chinese
Gemma 4 26B A4B TAIDE zhTW is a 25.2B parameter multimodal model with 4B active parameters in a mixture of experts. It supports text and vision and is fine‑tuned on TAIDE Taiwanese Traditional Chinese data. The model is released under Apache‑2.0 with additional TAIDE license restrictions.
Good at
- Multimodal text‑image dialogue
- Traditional Chinese language tasks
- Reasoning and tool use
Limits
- No support for other modalities
- Requires 8k context for memory estimates
- License restricts military or illegal use
Best for
- Chatbot in Traditional Chinese
- Image‑to‑text generation
- Local inference with GGUF
Who it’s for. Developers building local Chinese chatbots or image‑text applications who need a fully open‑source model with vision support. The model is suitable for on‑premise deployment in compliance with Apache‑2.0 and TAIDE terms.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_M | 10.4 GB | 18.9 GB | Too big | Get file → | |
| IQ4_XS | 13.9 GB | 22.5 GB | Too big | Get file → | |
| Q4_K_M | 16.8 GB | 25.3 GB | Too big | Get file → | |
| Q5_K_M | 19.1 GB | 27.7 GB | Too big | Get file → | |
| Q6_K | 22.6 GB | 31.2 GB | Too big | Get file → | |
| Q8_0 | 26.9 GB | 35.4 GB | Too big | Get file → |
For 8 GB VRAM, use IQ4_XS (13.92 GB) or Q4_K_M (16.8 GB). For 12 GB VRAM, Q5_K_M (19.13 GB) or Q6_K (22.64 GB) are suitable. For 16 GB VRAM, Q8_0 (26.86 GB) provides the highest quality.
What GPU do you need for Gemma 4 26B A4B TAIDE zhTW?
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 IQ4_XS (13.9 GB file, about 22.5 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (22.6 GB file, about 31.2 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (26.9 GB file, about 35.4 GB in use).
Which Gemma 4 26B A4B TAIDE zhTW quant should you choose?
Q4_K_M is the usual starting point for Gemma 4 26B A4B TAIDE zhTW: it balances file size and quality well. Here it is a 16.8 GB file.
The Q8_0 file is 26.9 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 IQ2_M at 10.4 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Gemma 4 26B A4B TAIDE zhTW
How much VRAM does Gemma 4 26B A4B TAIDE zhTW need?
About 25.3 GB at Q4_K_M with an 8K context window. That is the 16.8 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 TAIDE zhTW on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 18.9 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Gemma 4 26B A4B TAIDE zhTW GGUF?
It depends on the quant: IQ2_M is 10.4 GB, IQ4_XS is 13.9 GB, Q4_K_M is 16.8 GB, Q5_K_M is 19.1 GB, Q6_K is 22.6 GB, Q8_0 is 26.9 GB.
What context length does Gemma 4 26B A4B TAIDE zhTW 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 TAIDE zhTW GGUF?
The files are on Hugging Face in the xCloudinfo/Gemma-4-26B-A4B-TAIDE-zhTW-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 TAIDE zhTW 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 this model on 8 GB VRAM?
Yes, use the IQ4_XS or Q4_K_M quantized files, which fit within 8 GB VRAM with approximate memory usage of 22.5 GB and 25.3 GB respectively.
Does the model support vision?
Yes, the GGUF version includes a vision projector (mmproj) for image‑to‑text tasks.
What license applies to this model?
The model is licensed under Apache‑2.0 with additional TAIDE license terms that prohibit military or illegal use.