SD

SDS 3M

SdsGGUF by jkong0221Updated 2024-07-10
Download on Hugging Face
Parameters8.03B
Context8K
Layers32
Architecturellama
Smallest quant4.9 GB
Quick answer

SDS 3M needs about 6.5 GB of memory at Q4_K_M (a 4.9 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 2 quants, from 4.9 GB (Q4_K_M) to 16.1 GB (F16).

SDS 3M is a 8.03B-parameter Sds model in GGUF format, quantized by jkong0221. Its trained context length is 8K tokens. The repository has 2 quant files, from 4.9 GB (Q4_K_M) to 16.1 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M4.9 GB 6.5 GB
Fits Get file →
F1616.1 GB 17.6 GB
Too big Get file →

What GPU do you need for SDS 3M?

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: the best quant that fits is Q4_K_M (4.9 GB file, about 6.5 GB in use).
  • 12 GB VRAM: the best quant that fits is Q4_K_M (4.9 GB file, about 6.5 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_K_M (4.9 GB file, about 6.5 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (16.1 GB file, about 17.6 GB in use).

Which SDS 3M quant should you choose?

Q4_K_M is the usual starting point for SDS 3M: it balances file size and quality well. Here it is a 4.9 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters8.03B
Layers32
Trained context8,192 tokens
KV cache (fp16)128 KB per token

Source

Quantized byjkong0221
FamilySds
Downloads (HF)7
Last updated2024-07-10

Frequently asked questions about SDS 3M

How much VRAM does SDS 3M need?

About 6.5 GB at Q4_K_M with an 8K context window. That is the 4.9 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 SDS 3M on an 8 GB GPU?

Yes, with Q4_K_M: the 4.9 GB file needs about 6.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of SDS 3M GGUF?

It depends on the quant: Q4_K_M is 4.9 GB, F16 is 16.1 GB.

What context length does SDS 3M support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 1.1 GB at 8K and 1.1 GB at 8K.

Where can I download SDS 3M GGUF?

The files are on Hugging Face in the jkong0221/SDS_3M repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from jkong0221

All by jkong0221 →

More Sds models

All Sds →

Other small models

All small models →