MA

Mangaba Base 91M

MangabaGGUF by mangaba-aiUpdated 2026-11-05
Download on Hugging Face
Parameters91M
Context512
Layers14
Architectureqwen3
Smallest quant0.1 GB
Quick answer

Mangaba Base 91M needs about 0.7 GB of memory at Q8_0 (a 0.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 0.1 GB (Q8_0) to 0.2 GB (F16).

Mangaba Base 91M is a 91M-parameter Mangaba model in GGUF format, quantized by mangaba-ai. Its trained context length is 512 tokens. The repository has 2 quant files, from 0.1 GB (Q8_0) to 0.2 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_00.1 GB 0.6 GB
Fits Get file →
F160.2 GB 0.7 GB
Fits Get file →

What GPU do you need for Mangaba Base 91M?

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 (0.2 GB file, about 0.8 GB in use).

Which Mangaba Base 91M quant should you choose?

Q8_0 (0.1 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen3
Parameters91M
Layers14
Trained context512 tokens
KV cache (fp16)14 KB per token

Source

Quantized bymangaba-ai
FamilyMangaba
Licenseapache-2.0
Downloads (HF)198
Last updated2026-11-05

Frequently asked questions about Mangaba Base 91M

How much VRAM does Mangaba Base 91M need?

About 0.7 GB at Q8_0 with an 8K context window. That is the 0.1 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 Mangaba Base 91M on an 8 GB GPU?

Yes, with F16: the 0.2 GB file needs about 0.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Mangaba Base 91M GGUF?

It depends on the quant: Q8_0 is 0.1 GB, F16 is 0.2 GB.

What context length does Mangaba Base 91M support?

The GGUF header lists a trained context length of 512 tokens (512). The KV cache grows with the context you use: about 0.1 GB at 8K and 0.0 GB at 512.

Where can I download Mangaba Base 91M GGUF?

The files are on Hugging Face in the mangaba-ai/Mangaba-Base-91M repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Mangaba Base 91M 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 mangaba-ai

All by mangaba-ai →

More Mangaba models

All Mangaba →

Other tiny models

All tiny models →