SE

wa search

SearchGGUF by davidpuUpdated 2026-11-04
Download on Hugging Face
Parameters568M
Context512
Layers24
Architecturebert
Smallest quant1.1 GB
Quick answer

wa search needs about 2.4 GB of memory at F16 (a 1.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 1.1 GB (F16) to 1.2 GB (F16).

wa search is a 568M-parameter Search model in GGUF format, quantized by davidpu. Its trained context length is 512 tokens. The repository has 2 quant files, from 1.1 GB (F16) to 1.2 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F161.1 GB 1.7 GB
Fits Get file →
F161.2 GB 1.7 GB
Fits Get file →

What GPU do you need for wa search?

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 (1.2 GB file, about 2.5 GB in use).

Which wa search quant should you choose?

F16 (1.1 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturebert
Parameters568M
Layers24
Trained context512 tokens
KV cache (fp16)96 KB per token

Source

Quantized bydavidpu
FamilySearch
Downloads (HF)124
Last updated2026-11-04

Frequently asked questions about wa search

How much VRAM does wa search need?

About 2.4 GB at F16 with an 8K context window. That is the 1.1 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 wa search on an 8 GB GPU?

Yes, with F16: the 1.2 GB file needs about 2.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of wa search GGUF?

It depends on the quant: F16 is 1.1 GB, F16 is 1.2 GB.

What context length does wa search support?

The GGUF header lists a trained context length of 512 tokens (512). The KV cache grows with the context you use: about 0.8 GB at 8K and 0.1 GB at 512.

Where can I download wa search GGUF?

The files are on Hugging Face in the davidpu/wa-search-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from davidpu

All by davidpu →

More Search models

All Search →

Other tiny models

All tiny models →