TE

Tess XS v1.0 GGUF fp16

TessGGUF by ddh0Updated 2023-11-16
Download on Hugging Face
Parameters7.24B
Context32K
Layers32
Architecturellama
Smallest quant7.8 GB
Quick answer

Tess XS v1.0 GGUF fp16 needs about 9.4 GB of memory at Q8_0 (a 7.8 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 2 quants, from 7.8 GB (Q8_0) to 14.5 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Tess XS v1.0 GGUF fp16 is a 7.24B-parameter Tess model in GGUF format, quantized by ddh0. Its trained context length is 32K tokens. The repository has 2 quant files, from 7.8 GB (Q8_0) to 14.5 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_07.8 GB 9.4 GB
Too big Get file →
—14.5 GB 16.1 GB
Too big Get file →

What GPU do you need for Tess XS v1.0 GGUF fp16?

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 Q8_0 (7.8 GB file, about 9.4 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (7.8 GB file, about 9.4 GB in use).
  • 24 GB VRAM: the best quant that fits is the main file (14.5 GB file, about 16.1 GB in use).

Which Tess XS v1.0 GGUF fp16 quant should you choose?

Q8_0 (7.8 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
Parameters7.24B
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized byddh0
FamilyTess
Licenseapache-2.0
Downloads (HF)27
Last updated2023-11-16

Frequently asked questions about Tess XS v1.0 GGUF fp16

How much VRAM does Tess XS v1.0 GGUF fp16 need?

About 9.4 GB at Q8_0 with an 8K context window. That is the 7.8 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 Tess XS v1.0 GGUF fp16 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 9.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Tess XS v1.0 GGUF fp16 GGUF?

It depends on the quant: Q8_0 is 7.8 GB, file is 14.5 GB.

What context length does Tess XS v1.0 GGUF fp16 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download Tess XS v1.0 GGUF fp16 GGUF?

The files are on Hugging Face in the ddh0/Tess-XS-v1.0-GGUF-fp16 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Tess XS v1.0 GGUF fp16 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 ddh0

All by ddh0 →

More Tess models

All Tess →

Other small models

All small models →