UM

UMBASA.1B.i1 Q3 k L

UmbasaGGUF by UmbasaUpdated 2026-07-24
Download on Hugging Face
Parameters1B
Context32K
Layers26
Architecturegemma3
Smallest quant0.8 GB
Quick answer

UMBASA.1B.i1 Q3 k L needs about 1.5 GB of memory at Q3_K_L (a 0.8 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 0.9 GB.

UMBASA.1B.i1 Q3 k L is a 1B-parameter Umbasa model in GGUF format, quantized by Umbasa. Its trained context length is 32K tokens. The repository has 1 quant file, from 0.8 GB (Q3_K_L) to 0.8 GB (Q3_K_L).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_L0.8 GB 1.5 GB
Fits Get file →

What GPU do you need for UMBASA.1B.i1 Q3 k L?

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 Q3_K_L (0.8 GB file, about 1.5 GB in use).

Which UMBASA.1B.i1 Q3 k L quant should you choose?

Q3_K_L (0.8 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegemma3
Parameters1B
Layers26
Trained context32,768 tokens
KV cache (fp16)26 KB per token

Source

Quantized byUmbasa
FamilyUmbasa
Licenseopenrail
Downloads (HF)4
Last updated2026-07-24

Frequently asked questions about UMBASA.1B.i1 Q3 k L

How much VRAM does UMBASA.1B.i1 Q3 k L need?

About 1.5 GB at Q3_K_L with an 8K context window. That is the 0.8 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 UMBASA.1B.i1 Q3 k L on an 8 GB GPU?

Yes, with Q3_K_L: the 0.8 GB file needs about 1.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of UMBASA.1B.i1 Q3 k L GGUF?

It depends on the quant: Q3_K_L is 0.8 GB.

What context length does UMBASA.1B.i1 Q3 k L support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.9 GB at 32K.

Where can I download UMBASA.1B.i1 Q3 k L GGUF?

The files are on Hugging Face in the Umbasa/UMBASA.1B.i1-Q3_k_L repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does UMBASA.1B.i1 Q3 k L use?

Hugging Face lists the license as openrail. 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 →

Other tiny models

All tiny models →