SH

HF

ShaythuramGGUF by shaythuramUpdated 2025-02-26
Download on Hugging Face
Parameters3.61B
Context128K
Layers28
Architecturellama
Smallest quant3.8 GB
Quick answer

HF needs about 5.3 GB of memory at Q8_0 (a 3.8 GB file) with an 8K context window, so it fits on a 6 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.

HF is a 3.61B-parameter Shaythuram model in GGUF format, quantized by shaythuram. Its trained context length is 128K tokens. The repository has 1 quant file, from 3.8 GB (Q8_0) to 3.8 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_03.8 GB 5.3 GB
Fits Get file →

What GPU do you need for HF?

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: the best quant that fits is Q8_0 (3.8 GB file, about 5.3 GB in use).

Which HF quant should you choose?

Q8_0 (3.8 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters3.61B
Layers28
Trained context131,072 tokens
KV cache (fp16)112 KB per token

Source

Quantized byshaythuram
Repositoryshaythuram/HF
Licenseapache-2.0
Downloads (HF)22
Last updated2025-02-26

Frequently asked questions about HF

How much VRAM does HF need?

About 5.3 GB at Q8_0 with an 8K context window. That is the 3.8 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 HF on an 8 GB GPU?

Yes, with Q8_0: the 3.8 GB file needs about 5.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of HF GGUF?

It depends on the quant: Q8_0 is 3.8 GB.

What context length does HF support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.8 GB at 32K.

Where can I download HF GGUF?

The files are on Hugging Face in the shaythuram/HF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does HF 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.

Similar models

Browse all →

More from shaythuram

All by shaythuram →

Other small models

All small models →