Akhet Ra1 needs about 3.5 GB of memory at Q4_K_M (a 2.7 GB file) with an 8K context window, so it fits on a 4 GB GPU.
Akhet Ra1 is a 4.21B-parameter Qwen model in GGUF format, quantized by alwkala. Its trained context length is 256K tokens. The repository has 1 quant file, from 2.7 GB (Q4_K_M) to 2.7 GB (Q4_K_M).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 2.7 GB | 3.5 GB | Fits | Get file → |
What GPU do you need for Akhet Ra1?
These figures add the file size, an fp16 KV cache at an 8K context window 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: the best quant that fits is Q4_K_M (2.7 GB file, about 3.5 GB in use).
Which Akhet Ra1 quant should you choose?
Q4_K_M is the usual starting point for Akhet Ra1: it balances file size and quality well. Here it is a 2.7 GB file.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Akhet Ra1
How much VRAM does Akhet Ra1 need?
About 3.5 GB at Q4_K_M with an 8K context window. That is the 2.7 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 Akhet Ra1 on an 8 GB GPU?
Yes, with Q4_K_M: the 2.7 GB file needs about 3.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Akhet Ra1 GGUF?
It depends on the quant: Q4_K_M is 2.7 GB.
What context length does Akhet Ra1 support?
The GGUF header lists a trained context length of 262,144 tokens (256K).
Where can I download Akhet Ra1 GGUF?
The files are on Hugging Face in the alwkala/Akhet-Ra1 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Akhet Ra1 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.