Orion 26B A4B v1b needs about 22.5 GB of memory at IQ4_XS (a 13.9 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.
Orion 26B A4B v1b is a 25.2B-parameter Orion model in GGUF format, quantized by Phil2Sat. Its trained context length is 256K tokens. The repository has 1 quant file, from 13.9 GB (IQ4_XS) to 13.9 GB (IQ4_XS).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ4_XS | 13.9 GB | 22.5 GB | Too big | Get file → |
What GPU do you need for Orion 26B A4B v1b?
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).
Which Orion 26B A4B v1b quant should you choose?
IQ4_XS (13.9 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Orion 26B A4B v1b
How much VRAM does Orion 26B A4B v1b need?
About 22.5 GB at IQ4_XS with an 8K context window. That is the 13.9 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 Orion 26B A4B v1b on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 22.5 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Orion 26B A4B v1b GGUF?
It depends on the quant: IQ4_XS is 13.9 GB.
What context length does Orion 26B A4B v1b 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 Orion 26B A4B v1b GGUF?
The files are on Hugging Face in the Phil2Sat/Orion-26B-A4B-v1b repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Orion 26B A4B v1b 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.