SA

SamModel

SammodelGGUF by SansarKUpdated 2024-07-17
Download on Hugging Face
Parameters514M
Context8K
Layers16
Architecturellama
Smallest quant0.3 GB
Quick answer

SamModel needs about 1.2 GB of memory at Q4_K_S (a 0.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 0.3 GB (Q4_K_S) to 1.0 GB (F16).

SamModel is a 514M-parameter Sammodel model in GGUF format, quantized by SansarK. Its trained context length is 8K tokens. The repository has 2 quant files, from 0.3 GB (Q4_K_S) to 1.0 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_S0.3 GB 1.2 GB
Fits Get file →
F161.0 GB 1.9 GB
Fits Get file →

What GPU do you need for SamModel?

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 F16 (1.0 GB file, about 1.9 GB in use).

Which SamModel quant should you choose?

Q4_K_S (0.3 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

Architecturellama
Parameters514M
Layers16
Trained context8,192 tokens
KV cache (fp16)48 KB per token

Source

Quantized bySansarK
FamilySammodel
Licensemit
Downloads (HF)10
Last updated2024-07-17

Frequently asked questions about SamModel

How much VRAM does SamModel need?

About 1.2 GB at Q4_K_S with an 8K context window. That is the 0.3 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 SamModel on an 8 GB GPU?

Yes, with F16: the 1.0 GB file needs about 1.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of SamModel GGUF?

It depends on the quant: Q4_K_S is 0.3 GB, F16 is 1.0 GB.

What context length does SamModel support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 0.4 GB at 8K and 0.4 GB at 8K.

Where can I download SamModel GGUF?

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

What license does SamModel 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 →

Other tiny models

All tiny models →