UL

UltraBERT-Embed-150M

UltrabertGGUF by cstrUpdated 2026-11-07
Download on Hugging Face
Parameters151M
Context32K
Layers24
Architectureultrabert
Smallest quant0.6 GB
Quick answer

UltraBERT-Embed-150M needs about 1.7 GB of memory at Q4_K (a 0.6 GB file) with an 8K context window, so it fits on a 4 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 2.4 GB.

UltraBERT-Embed-150M is a 151M-parameter Ultrabert model in GGUF format, quantized by cstr. Its trained context length is 32K tokens. The repository has 1 quant file, from 0.6 GB (Q4_K) to 0.6 GB (Q4_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K0.6 GB 1.7 GB
Fits Get file →

What GPU do you need for UltraBERT-Embed-150M?

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 Q4_K (0.6 GB file, about 1.7 GB in use).

Which UltraBERT-Embed-150M quant should you choose?

Q4_K (0.6 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureultrabert
Parameters151M
Layers24
Trained context32,768 tokens
KV cache (fp16)72 KB per token

Source

Quantized bycstr
FamilyUltrabert
Licenseapache-2.0
Downloads (HF)81
Last updated2026-11-07

Frequently asked questions about UltraBERT-Embed-150M

How much VRAM does UltraBERT-Embed-150M need?

About 1.7 GB at Q4_K with an 8K context window. That is the 0.6 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 UltraBERT-Embed-150M on an 8 GB GPU?

Yes, with Q4_K: the 0.6 GB file needs about 1.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of UltraBERT-Embed-150M GGUF?

It depends on the quant: Q4_K is 0.6 GB.

What context length does UltraBERT-Embed-150M support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.6 GB at 8K and 2.4 GB at 32K.

Where can I download UltraBERT-Embed-150M GGUF?

The files are on Hugging Face in the cstr/UltraBERT-Embed-150M-CrispEmbed-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 UltraBERT-Embed-150M 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 from cstr

All by cstr →

Other tiny models

All tiny models →