PA

palmer-004-turbo

PalmerGGUF by ZeroWwUpdated 2024-07-17
Download on Hugging Face
Parameters514M
Context8K
Layers16
Architecturellama
Smallest quant0.5 GB
Quick answer

palmer-004-turbo needs about 1.4 GB of memory at its main file (a 0.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 5 quants, from 0.5 GB (Q5_K) to 1.0 GB (F16).

palmer-004-turbo is a 514M-parameter Palmer model in GGUF format, quantized by ZeroWw. Its trained context length is 8K tokens. The repository has 5 quant files, from 0.5 GB (Q5_K) to 1.0 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K0.5 GB 1.4 GB
Fits Get file →
Q6_K0.5 GB 1.4 GB
Fits Get file →
—0.5 GB 1.4 GB
Fits Get file →
Q8_00.6 GB 1.5 GB
Fits Get file →
F161.0 GB 1.9 GB
Fits Get file →

What GPU do you need for palmer-004-turbo?

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 F16 (1.0 GB file, about 1.9 GB in use).

Which palmer-004-turbo quant should you choose?

If memory is tight, the smallest file is Q5_K at 0.5 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
Parameters514M
Layers16
Trained context8,192 tokens
KV cache (fp16)48 KB per token

Source

Quantized byZeroWw
FamilyPalmer
Licensemit
Downloads (HF)100
Last updated2024-07-17

Frequently asked questions about palmer-004-turbo

How much VRAM does palmer-004-turbo need?

About 1.4 GB at its main file with an 8K context window. That is the 0.5 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 palmer-004-turbo on an 8 GB GPU?

Yes, with F16: the 1.0 GB file needs about 1.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of palmer-004-turbo GGUF?

It depends on the quant: Q5_K is 0.5 GB, Q6_K is 0.5 GB, file is 0.5 GB, Q8_0 is 0.6 GB, F16 is 1.0 GB.

What context length does palmer-004-turbo support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 0.4 GB at 8K and 0.4 GB at 8K.

Where can I download palmer-004-turbo GGUF?

The files are on Hugging Face in the ZeroWw/palmer-004-turbo-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 palmer-004-turbo use?

Hugging Face lists the license as mit. 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 ZeroWw

All by ZeroWw →

More Palmer models

All Palmer →

Other tiny models

All tiny models →