TO

TowerInstruct 7B v0.2

TowerinstructGGUF by arzethUpdated 2024-02-24
Download on Hugging Face
Parameters6.74B
Context4K
Layers32
Architecturellama
Smallest quant2.8 GB
Quick answer

TowerInstruct 7B v0.2 needs about 8.6 GB of memory at IQ4_NL (a 3.8 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 6 quants, from 2.8 GB (IQ3_XXS) to 7.2 GB (Q8_0).

TowerInstruct 7B v0.2 is a 6.74B-parameter Towerinstruct model in GGUF format, quantized by arzeth. Its trained context length is 4K tokens. The repository has 6 quant files, from 2.8 GB (IQ3_XXS) to 7.2 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ3_XXS2.8 GB 5.5 GB
Fits Get file →
IQ3_M3.1 GB 5.8 GB
Fits Get file →
IQ4_NL3.8 GB 6.5 GB
Fits Get file →
Q5_K_M4.8 GB 7.4 GB
Tight Get file →
Q6_K5.5 GB 8.2 GB
Too big Get file →
Q8_07.2 GB 9.8 GB
Too big Get file →

What GPU do you need for TowerInstruct 7B v0.2?

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 IQ3_M (3.1 GB file, about 7.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (7.2 GB file, about 12.0 GB in use).

Which TowerInstruct 7B v0.2 quant should you choose?

IQ4_NL (3.8 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

If memory is tight, the smallest file is IQ3_XXS at 2.8 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters6.74B
Layers32
Trained context4,096 tokens
KV cache (fp16)512 KB per token

Source

Quantized byarzeth
Downloads (HF)182
Last updated2024-02-24

Frequently asked questions about TowerInstruct 7B v0.2

How much VRAM does TowerInstruct 7B v0.2 need?

About 8.6 GB at IQ4_NL with an 8K context window. That is the 3.8 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 TowerInstruct 7B v0.2 on an 8 GB GPU?

Yes, with IQ3_M: the 3.1 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of TowerInstruct 7B v0.2 GGUF?

It depends on the quant: IQ3_XXS is 2.8 GB, IQ3_M is 3.1 GB, IQ4_NL is 3.8 GB, Q5_K_M is 4.8 GB, Q6_K is 5.5 GB, Q8_0 is 7.2 GB.

What context length does TowerInstruct 7B v0.2 support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 4.3 GB at 8K and 2.1 GB at 4K.

Where can I download TowerInstruct 7B v0.2 GGUF?

The files are on Hugging Face in the arzeth/TowerInstruct-7B-v0.2-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 7B v0.2 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-7B-v0.2

Similar models

Browse all →

More from arzeth

All by arzeth →

More Towerinstruct models

All Towerinstruct →

Other small models

All small models →