UM

Umbuzo 1.1B Chat v5 Web Merged

UmbuzoGGUF by DomSimoneUpdated 2026-03-09
Download on Hugging Face
Parameters3.09B
Context32K
Layers36
Architectureqwen2
Smallest quant6.2 GB
Quick answer

Umbuzo 1.1B Chat v5 Web Merged needs about 7.0 GB of memory at F16 (a 6.2 GB file) with an 8K context window, so it fits on a 8 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 1.2 GB.

Umbuzo 1.1B Chat v5 Web Merged is a 3.09B-parameter Umbuzo model in GGUF format, quantized by DomSimone. Its trained context length is 32K tokens. The repository has 1 quant file, from 6.2 GB (F16) to 6.2 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F166.2 GB 7.0 GB
Fits Get file →

What GPU do you need for Umbuzo 1.1B Chat v5 Web Merged?

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 F16 (6.2 GB file, about 7.0 GB in use).

Which Umbuzo 1.1B Chat v5 Web Merged quant should you choose?

F16 (6.2 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

Architectureqwen2
Parameters3.09B
Layers36
Trained context32,768 tokens
KV cache (fp16)36 KB per token

Source

Quantized byDomSimone
FamilyUmbuzo
Downloads (HF)6
Last updated2026-03-09

Frequently asked questions about Umbuzo 1.1B Chat v5 Web Merged

How much VRAM does Umbuzo 1.1B Chat v5 Web Merged need?

About 7.0 GB at F16 with an 8K context window. That is the 6.2 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 Umbuzo 1.1B Chat v5 Web Merged on an 8 GB GPU?

Yes, with F16: the 6.2 GB file needs about 7.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Umbuzo 1.1B Chat v5 Web Merged GGUF?

It depends on the quant: F16 is 6.2 GB.

What context length does Umbuzo 1.1B Chat v5 Web Merged support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.3 GB at 8K and 1.2 GB at 32K.

Where can I download Umbuzo 1.1B Chat v5 Web Merged GGUF?

The files are on Hugging Face in the DomSimone/Umbuzo 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 DomSimone

All by DomSimone →

Other tiny models

All tiny models →