RA

X Ray Alpha

RayGGUF by l3utterflyUpdated 2025-03-31
Download on Hugging Face
Parameters3.88B
Context128K
Layers34
Architecturegemma3
Smallest quant1.7 GB
Quick answer

X Ray Alpha needs about 4.8 GB of memory at Q6_K (a 3.2 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 5 quants, from 1.7 GB (Q2_K) to 7.8 GB (F32). Longer context needs more: at 32K tokens the KV cache alone adds about 4.6 GB.

X Ray Alpha is a 3.88B-parameter Ray model in GGUF format, quantized by l3utterfly. Its trained context length is 128K tokens. The repository has 5 quant files, from 1.7 GB (Q2_K) to 7.8 GB (F32).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K1.7 GB 3.4 GB
Fits Get file →
Q4_K2.5 GB 4.1 GB
Fits Get file →
Q6_K3.2 GB 4.8 GB
Fits Get file →
Q8_04.1 GB 5.8 GB
Fits Get file →
F327.8 GB 9.4 GB
Too big Get file →

What GPU do you need for X Ray Alpha?

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: the best quant that fits is Q2_K (1.7 GB file, about 3.4 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (4.1 GB file, about 5.8 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (4.1 GB file, about 5.8 GB in use).
  • 12 GB VRAM: the best quant that fits is F32 (7.8 GB file, about 9.4 GB in use).

Which X Ray Alpha quant should you choose?

Q6_K (3.2 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.

If memory is tight, the smallest file is Q2_K at 1.7 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

Architecturegemma3
Parameters3.88B
Layers34
Trained context131,072 tokens
KV cache (fp16)136 KB per token

Source

Quantized byl3utterfly
FamilyRay
Licensegemma
Downloads (HF)76
Last updated2025-03-31

Frequently asked questions about X Ray Alpha

How much VRAM does X Ray Alpha need?

About 4.8 GB at Q6_K with an 8K context window. That is the 3.2 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 X Ray Alpha on an 8 GB GPU?

Yes, with Q8_0: the 4.1 GB file needs about 5.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of X Ray Alpha GGUF?

It depends on the quant: Q2_K is 1.7 GB, Q4_K is 2.5 GB, Q6_K is 3.2 GB, Q8_0 is 4.1 GB, F32 is 7.8 GB.

What context length does X Ray Alpha support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.6 GB at 32K.

Where can I download X Ray Alpha GGUF?

The files are on Hugging Face in the l3utterfly/X-Ray_Alpha-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 X Ray Alpha use?

Hugging Face lists the license as gemma. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Similar models

Browse all →

More from l3utterfly

All by l3utterfly →

More Ray models

All Ray →

Other small models

All small models →