RF

rfdetr cpp seg nano

RfdetrGGUF by mudlerUpdated 2026-05-27
Download on Hugging Face
Parameters33M
Context—
Layers—
Architecturerfdetr
Smallest quant0.0 GB
Quick answer

rfdetr cpp seg nano needs about 0.5 GB of memory at Q8_0 (a 0.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 0.0 GB (Q4_K) to 0.1 GB (F32).

RF-DETR Seg-Nano – lightweight instance segmentation

RF-DETR Seg-Nano is a 0.0333 B parameter model based on DINOv2‑small. It performs instance segmentation with 78×78 masks per query. The GGUF format supports multiple quantizations for CPU use.

Good at

  • Fast CPU inference
  • Small model size
  • Accurate on COCO val2017

Limits

  • No vision support beyond 312×312 input
  • Limited to CPU inference
  • License is Apache‑2.0

Best for

  • Embedded inference
  • Edge devices
  • Rapid prototyping

Who it’s for. Developers needing a compact segmentation model for C++/ggml environments. The model is suitable for applications where memory is limited but accurate instance masks are required.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K0.0 GB 0.5 GB
Fits Get file →
Q8_00.0 GB 0.5 GB
Fits Get file →
F160.1 GB 0.6 GB
Fits Get file →
F320.1 GB 0.6 GB
Fits Get file →

For most users, the F16 quantization (0.07 GB, 0.6 GB memory at 8k context) is recommended. If memory is tighter, Q8_0 (0.04 GB, 0.5 GB memory) offers a good trade‑off. For very small storage budgets, Q4_K (0.03 GB, 0.5 GB memory) can be used, but expect a slight drop in recall.

What GPU do you need for rfdetr cpp seg nano?

These figures add the file size, an fp16 KV cache at an 8K context window 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 F32 (0.1 GB file, about 0.6 GB in use).

Which rfdetr cpp seg nano quant should you choose?

Q8_0 (0.0 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.

If memory is tight, the smallest file is Q4_K at 0.0 GB, with the quality trade-offs that come with fewer bits. 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

Architecturerfdetr
Parameters33M

Source

Quantized bymudler
FamilyRfdetr
Licenseapache-2.0
Downloads (HF)741
Last updated2026-05-27

Frequently asked questions about rfdetr cpp seg nano

How much VRAM does rfdetr cpp seg nano need?

About 0.5 GB at Q8_0 with an 8K context window. That is the 0.0 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 rfdetr cpp seg nano on an 8 GB GPU?

Yes, with F32: the 0.1 GB file needs about 0.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of rfdetr cpp seg nano GGUF?

It depends on the quant: Q4_K is 0.0 GB, Q8_0 is 0.0 GB, F16 is 0.1 GB, F32 is 0.1 GB.

Where can I download rfdetr cpp seg nano GGUF?

The files are on Hugging Face in the mudler/rfdetr-cpp-seg-nano repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does rfdetr cpp seg nano 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.

Can I run RF‑DETR Seg‑Nano on a machine with 8 GB VRAM?

Yes, the model requires only about 0.5 GB of VRAM at 8k context, so it fits easily on 8 GB VRAM.

Is the model compatible with GPU inference?

The GGUF format is designed for CPU inference with rfdetr.cpp; GPU support is not provided in this release.

What is the recommended quantization for best accuracy?

F16 is the recommended default; it matches F32 accuracy while being smaller and faster on modern CPUs.

Similar models

Browse all →

More from mudler

All by mudler →

More Rfdetr models

All Rfdetr →

Other tiny models

All tiny models →