QU

quant tests

QuantGGUF by compiladeUpdated 2024-12-29
Download on Hugging Face
Parameters1.52B
Context2K
Layers24
Architecturellama
Smallest quant0.7 GB
Quick answer

quant tests needs about 3.0 GB of memory at TQ1_0 (a 0.9 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 3 quants, from 0.7 GB (TQ1_0) to 1.4 GB (TQ1_0).

quant tests is a 1.52B-parameter Quant model in GGUF format, quantized by compilade. Its trained context length is 2K tokens. The repository has 3 quant files, from 0.7 GB (TQ1_0) to 1.4 GB (TQ1_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
TQ1_00.7 GB 1.6 GB
Fits Get file →
TQ1_00.9 GB 1.8 GB
Fits Get file →
TQ1_01.4 GB 2.3 GB
Fits Get file →

What GPU do you need for quant tests?

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: the best quant that fits is TQ1_0 (1.4 GB file, about 3.5 GB in use).

Which quant tests quant should you choose?

TQ1_0 (0.9 GB) is the middle option in this repository. Lower bit counts mean smaller files and more quality loss.

If memory is tight, the smallest file is TQ1_0 at 0.7 GB, with the quality trade-offs that come with fewer bits. Lower bit counts mean smaller files and more quality loss.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters1.52B
Layers24
Trained context2,048 tokens
KV cache (fp16)192 KB per token

Source

Quantized bycompilade
FamilyQuant
Licenseapache-2.0
Downloads (HF)124
Last updated2024-12-29

Frequently asked questions about quant tests

How much VRAM does quant tests need?

About 3.0 GB at TQ1_0 with an 8K context window. That is the 0.9 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 quant tests on an 8 GB GPU?

Yes, with TQ1_0: the 1.4 GB file needs about 3.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of quant tests GGUF?

It depends on the quant: TQ1_0 is 0.7 GB, TQ1_0 is 0.9 GB, TQ1_0 is 1.4 GB.

What context length does quant tests support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 1.6 GB at 8K and 0.4 GB at 2K.

Where can I download quant tests GGUF?

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

What license does quant tests 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 Quant models

All Quant →

Other tiny models

All tiny models →