PO

poppins

PoppinsGGUF by winters0x64Updated 2025-02-28
Download on Hugging Face
Parameters620M
Context32K
Layers—
Architectureqwen2
Smallest quant0.3 GB
Quick answer

poppins needs about 0.8 GB of memory at its main file (a 0.3 GB file) with an 8K context window, so it fits on a 4 GB GPU.

poppins is a 620M-parameter Poppins model in GGUF format, quantized by winters0x64. Its trained context length is 32K tokens. The repository has 1 quant file, from 0.3 GB to 0.3 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.3 GB 0.8 GB
Fits Get file →

What GPU do you need for poppins?

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 the main file (0.3 GB file, about 0.8 GB in use).

Specifications

Architecture from the GGUF header

Architectureqwen2
Parameters620M
Trained context32,768 tokens

Source

Quantized bywinters0x64
FamilyPoppins
Downloads (HF)0
Last updated2025-02-28

Frequently asked questions about poppins

How much VRAM does poppins need?

About 0.8 GB at its main file with an 8K context window. That is the 0.3 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 poppins on an 8 GB GPU?

Yes, with the smaller files: the 0.3 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 poppins GGUF?

It depends on the quant: file is 0.3 GB.

What context length does poppins support?

The GGUF header lists a trained context length of 32,768 tokens (32K).

Where can I download poppins GGUF?

The files are on Hugging Face in the winters0x64/poppins 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 →

Other tiny models

All tiny models →