SA

Sam Q4 K S

SamGGUF by SansarKUpdated 2024-07-16
Download on Hugging Face
Parameters494M
Context32K
Layers24
Architectureqwen2
Smallest quant0.4 GB
Quick answer

Sam Q4 K S needs about 1.0 GB of memory at Q4_K_S (a 0.4 GB file) with an 8K context window, so it fits on a 4 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 0.4 GB.

Sam Q4 K S is a 494M-parameter Sam model in GGUF format, quantized by SansarK. Its trained context length is 32K tokens. The repository has 1 quant file, from 0.4 GB (Q4_K_S) to 0.4 GB (Q4_K_S).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_S0.4 GB 1.0 GB
Fits Get file →

What GPU do you need for Sam Q4 K S?

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 Q4_K_S (0.4 GB file, about 1.0 GB in use).

Which Sam Q4 K S quant should you choose?

Q4_K_S (0.4 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

Architectureqwen2
Parameters494M
Layers24
Trained context32,768 tokens
KV cache (fp16)12 KB per token

Source

Quantized bySansarK
FamilySam
Base modelSansarK/Sam
Licensemit
Downloads (HF)9
Last updated2024-07-16

Frequently asked questions about Sam Q4 K S

How much VRAM does Sam Q4 K S need?

About 1.0 GB at Q4_K_S with an 8K context window. That is the 0.4 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 Sam Q4 K S on an 8 GB GPU?

Yes, with Q4_K_S: the 0.4 GB file needs about 1.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Sam Q4 K S GGUF?

It depends on the quant: Q4_K_S is 0.4 GB.

What context length does Sam Q4 K S support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.1 GB at 8K and 0.4 GB at 32K.

Where can I download Sam Q4 K S GGUF?

The files are on Hugging Face in the SansarK/Sam-Q4_K_S-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 Sam Q4 K S use?

Hugging Face lists the license as mit. 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 SansarK

All by SansarK →

More Sam models

All Sam →

Other tiny models

All tiny models →