TO

TowerInstruct 13B v0.1 Q5 0

TowerinstructGGUF by HeenLightUpdated 2024-09-21
Download on Hugging Face
Parameters13B
Context4K
Layers40
Architecturellama
Smallest quant9.0 GB
Quick answer

TowerInstruct 13B v0.1 Q5 0 needs about 16.2 GB of memory at Q5_0 (a 9.0 GB file) with an 8K context window, so it fits on a 24 GB GPU.

TowerInstruct 13B v0.1 Q5 0 is a 13B-parameter Towerinstruct model in GGUF format, quantized by HeenLight. Its trained context length is 4K tokens. The repository has 1 quant file, from 9.0 GB (Q5_0) to 9.0 GB (Q5_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_09.0 GB 12.8 GB
Too big Get file →

What GPU do you need for TowerInstruct 13B v0.1 Q5 0?

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: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: the best quant that fits is Q5_0 (9.0 GB file, about 16.2 GB in use).

Which TowerInstruct 13B v0.1 Q5 0 quant should you choose?

Q5_0 (9.0 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters13B
Layers40
Trained context4,096 tokens
KV cache (fp16)800 KB per token

Source

Quantized byHeenLight
Downloads (HF)7
Last updated2024-09-21

Frequently asked questions about TowerInstruct 13B v0.1 Q5 0

How much VRAM does TowerInstruct 13B v0.1 Q5 0 need?

About 16.2 GB at Q5_0 with an 8K context window. That is the 9.0 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 TowerInstruct 13B v0.1 Q5 0 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 16.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of TowerInstruct 13B v0.1 Q5 0 GGUF?

It depends on the quant: Q5_0 is 9.0 GB.

What context length does TowerInstruct 13B v0.1 Q5 0 support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 6.7 GB at 8K and 3.4 GB at 4K.

Where can I download TowerInstruct 13B v0.1 Q5 0 GGUF?

The files are on Hugging Face in the HeenLight/TowerInstruct-13B-v0.1-Q5_0-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 TowerInstruct 13B v0.1 Q5 0 use?

Hugging Face lists the license as cc-by-nc-4.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Other GGUFs of TowerInstruct-13B-v0.1

Similar models

Browse all →

More Towerinstruct models

All Towerinstruct →

Other medium models

All medium models →