WS

WSDt

WsdtGGUF by o2satzUpdated 2024-02-06
Download on Hugging Face
Parameters7.24B
Context32K
Layers32
Architecturellama
Smallest quant4.8 GB
Quick answer

WSDt needs about 9.9 GB of memory at Q5_K_M (a 5.1 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 4 quants, from 4.8 GB (Q5_K_M) to 5.1 GB (Q5_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 17.2 GB.

WSDt is a 7.24B-parameter Wsdt model in GGUF format, quantized by o2satz. Its trained context length is 32K tokens. The repository has 4 quant files, from 4.8 GB (Q5_K_M) to 5.1 GB (Q5_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_M4.8 GB 9.6 GB
Too big Get file →
Q5_K_M5.1 GB 9.9 GB
Too big Get file →
Q5_K_M5.1 GB 9.9 GB
Too big Get file →
Q5_K_M5.1 GB 9.9 GB
Too big Get file →

What GPU do you need for WSDt?

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 Q5_K_M (5.1 GB file, about 9.9 GB in use).

Which WSDt quant should you choose?

Q5_K_M (5.1 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

If memory is tight, the smallest file is Q5_K_M at 4.8 GB, with the quality trade-offs that come with fewer bits. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters7.24B
Layers32
Trained context32,768 tokens
KV cache (fp16)512 KB per token

Source

Quantized byo2satz
FamilyWsdt
Repositoryo2satz/WSDt
Downloads (HF)15
Last updated2024-02-06

Frequently asked questions about WSDt

How much VRAM does WSDt need?

About 9.9 GB at Q5_K_M with an 8K context window. That is the 5.1 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 WSDt on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 9.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of WSDt GGUF?

It depends on the quant: Q5_K_M is 4.8 GB, Q5_K_M is 5.1 GB, Q5_K_M is 5.1 GB, Q5_K_M is 5.1 GB.

What context length does WSDt support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 4.3 GB at 8K and 17.2 GB at 32K.

Where can I download WSDt GGUF?

The files are on Hugging Face in the o2satz/WSDt 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 o2satz

All by o2satz →

Other small models

All small models →