RH

rhk sa 3.1 8b v1

RhkGGUF by starlab3030Updated 2025-03-30
Download on Hugging Face
Parameters8.17B
Context128K
Layers40
Architecturegranite
Smallest quant8.7 GB
Quick answer

rhk sa 3.1 8b v1 needs about 10.5 GB of memory at its main file (a 8.7 GB file) with an 8K context window, so it fits on a 12 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

rhk sa 3.1 8b v1 is a 8.17B-parameter Rhk model in GGUF format, quantized by starlab3030. Its trained context length is 128K tokens. The repository has 1 quant file, from 8.7 GB to 8.7 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—8.7 GB 10.5 GB
Too big Get file →

What GPU do you need for rhk sa 3.1 8b v1?

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: the best quant that fits is the main file (8.7 GB file, about 10.5 GB in use).

Specifications

Architecture from the GGUF header

Architecturegranite
Parameters8.17B
Layers40
Trained context131,072 tokens
KV cache (fp16)160 KB per token

Source

Quantized bystarlab3030
FamilyRhk
Licenseapache-2.0
Downloads (HF)4
Last updated2025-03-30

Frequently asked questions about rhk sa 3.1 8b v1

How much VRAM does rhk sa 3.1 8b v1 need?

About 10.5 GB at its main file with an 8K context window. That is the 8.7 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 rhk sa 3.1 8b v1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 10.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of rhk sa 3.1 8b v1 GGUF?

It depends on the quant: file is 8.7 GB.

What context length does rhk sa 3.1 8b v1 support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.

Where can I download rhk sa 3.1 8b v1 GGUF?

The files are on Hugging Face in the starlab3030/rhk_sa_3.1_8b_v1.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 rhk sa 3.1 8b v1 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.

Other GGUFs of rhk_sa_v0.1

Similar models

Browse all →

More Rhk models

All Rhk →

Other small models

All small models →