Khanh 4 26B A4B IT HA2 needs about 20.2 GB of memory at IQ3_XS (a 11.6 GB file) with an 8K context window, so it fits on a 24 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 32.2 GB.
Khanh 4 26B A4B IT HA2 is a 25.2B-parameter Gemma model in GGUF format, quantized by LeDuckhanh. Its trained context length is 256K tokens. The repository has 1 quant file, from 11.6 GB (IQ3_XS) to 11.6 GB (IQ3_XS).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ3_XS | 11.6 GB | 20.2 GB | Too big | Get file → |
What GPU do you need for Khanh 4 26B A4B IT HA2?
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 IQ3_XS (11.6 GB file, about 20.2 GB in use).
Which Khanh 4 26B A4B IT HA2 quant should you choose?
IQ3_XS (11.6 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Khanh 4 26B A4B IT HA2
How much VRAM does Khanh 4 26B A4B IT HA2 need?
About 20.2 GB at IQ3_XS with an 8K context window. That is the 11.6 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 Khanh 4 26B A4B IT HA2 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 20.2 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Khanh 4 26B A4B IT HA2 GGUF?
It depends on the quant: IQ3_XS is 11.6 GB.
What context length does Khanh 4 26B A4B IT HA2 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 Khanh 4 26B A4B IT HA2 GGUF?
The files are on Hugging Face in the LeDuckhanh/Khanh-4-26B-A4B-IT-HA2 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Khanh 4 26B A4B IT HA2 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.