PY

python reference models

PythonGGUF by hongyongjiangUpdated 2026-06-29
Download on Hugging Face
Parameters3.88B
Context128K
Layers16
Architecturellama
Smallest quant2.5 GB
Quick answer

python reference models needs about 7.6 GB of memory at its main file (a 6.8 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 8 quants, from 2.5 GB (F16) to 13.5 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 1.1 GB.

python reference models is a 3.88B-parameter Python model in GGUF format, quantized by hongyongjiang. Its trained context length is 128K tokens. The repository has 8 quant files, from 2.5 GB (F16) to 13.5 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F162.5 GB 3.2 GB
Fits Get file →
—6.2 GB 6.9 GB
Fits Get file →
F166.4 GB 7.2 GB
Tight Get file →
—6.8 GB 7.6 GB
Tight Get file →
F167.8 GB 8.5 GB
Too big Get file →
F168.1 GB 8.8 GB
Too big Get file →
—8.1 GB 8.8 GB
Too big Get file →
—13.5 GB 14.2 GB
Too big Get file →

What GPU do you need for python reference models?

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 (2.5 GB file, about 3.2 GB in use).
  • 6 GB VRAM: the best quant that fits is F16 (2.5 GB file, about 3.2 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (6.8 GB file, about 7.6 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (8.1 GB file, about 8.8 GB in use).
  • 16 GB VRAM: the best quant that fits is the main file (13.5 GB file, about 14.2 GB in use).

Which python reference models quant should you choose?

If memory is tight, the smallest file is F16 at 2.5 GB, with the quality trade-offs that come with fewer bits. 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

Architecturellama
Parameters3.88B
Layers16
Trained context131,072 tokens
KV cache (fp16)32 KB per token

Source

Quantized byhongyongjiang
FamilyPython
Licensellama3.2
Downloads (HF)17
Last updated2026-06-29

Frequently asked questions about python reference models

How much VRAM does python reference models need?

About 7.6 GB at its main file with an 8K context window. That is the 6.8 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 python reference models on an 8 GB GPU?

Yes, with the smaller files: the 6.8 GB file needs about 7.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of python reference models GGUF?

It depends on the quant: F16 is 2.5 GB, file is 6.2 GB, F16 is 6.4 GB, file is 6.8 GB, F16 is 7.8 GB, F16 is 8.1 GB and 2 more.

What context length does python reference models support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.3 GB at 8K and 1.1 GB at 32K.

Where can I download python reference models GGUF?

The files are on Hugging Face in the hongyongjiang/python-reference-models repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does python reference models use?

Hugging Face lists the license as llama3.2. 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 Python models

All Python →

Other small models

All small models →