MA

Mantis 50M

MantisGGUF by kash8080Updated 2026-11-03
Download on Hugging Face
Parameters49M
Context1K
Layers25
Architectureqwen3
Smallest quant0.1 GB
Quick answer

Mantis 50M needs about 0.7 GB of memory at F16 (a 0.1 GB file) with an 8K context window, so it fits on a 4 GB GPU.

Mantis 50M is a 49M-parameter Mantis model in GGUF format, quantized by kash8080. Its trained context length is 1K tokens. The repository has 1 quant file, from 0.1 GB (F16) to 0.1 GB (F16).

Quants & memory

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

What GPU do you need for Mantis 50M?

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 (0.1 GB file, about 0.7 GB in use).

Which Mantis 50M quant should you choose?

F16 (0.1 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

Architectureqwen3
Parameters49M
Layers25
Trained context1,024 tokens
KV cache (fp16)13 KB per token

Source

Quantized bykash8080
FamilyMantis
Downloads (HF)131
Last updated2026-11-03

Frequently asked questions about Mantis 50M

How much VRAM does Mantis 50M need?

About 0.7 GB at F16 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 Mantis 50M on an 8 GB GPU?

Yes, with F16: the 0.1 GB file needs about 0.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Mantis 50M GGUF?

It depends on the quant: F16 is 0.1 GB.

What context length does Mantis 50M support?

The GGUF header lists a trained context length of 1,024 tokens (1K). The KV cache grows with the context you use: about 0.1 GB at 8K and 0.0 GB at 1K.

Where can I download Mantis 50M GGUF?

The files are on Hugging Face in the kash8080/Mantis-50M-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 Mantis 50M use?

Hugging Face lists the license as cc-by-nc-4.0. 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 kash8080

All by kash8080 →

More Mantis models

All Mantis →

Other tiny models

All tiny models →