theOG-50M-v12 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 0.1 GB (F16).
theOG-50M-v12 – a 50M‑parameter Python code model
theOG-50M-v12 is a 50M‑parameter Qwen3 model trained from scratch to generate Python code. It is available in Q8_0 and F16 GGUF formats and can run fully offline on a laptop.
Good at
- Python code generation
- small model size
- offline usage
Limits
- No vision support
- trained context 2048 tokens
- no mixture of experts
Best for
- Writing small Python functions
- educational coding examples
- quick prototyping
Who it’s for. Developers needing a lightweight code assistant that runs locally. Researchers testing code generation models on modest hardware.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 0.1 GB | 0.6 GB | Fits | Get file → | |
| F16 | 0.1 GB | 0.6 GB | Fits | Get file → |
For 8 GB VRAM, the Q8_0 quant (~0.7 GB memory at 8k context) fits comfortably. If more VRAM is available, the F16 quant (~0.8 GB) offers slightly higher precision. Both are small enough for ordinary laptops.
What GPU do you need for theOG-50M-v12?
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 0.8 GB in use).
Which theOG-50M-v12 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
Source
Frequently asked questions about theOG-50M-v12
How much VRAM does theOG-50M-v12 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 theOG-50M-v12 on an 8 GB GPU?
Yes, with F16: the 0.1 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 theOG-50M-v12 GGUF?
It depends on the quant: Q8_0 is 0.1 GB, F16 is 0.1 GB.
What context length does theOG-50M-v12 support?
The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.0 GB at 2K.
Where can I download theOG-50M-v12 GGUF?
The files are on Hugging Face in the DrunkkToys/theOG-50M repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does theOG-50M-v12 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 theOG-50M-v12 on 8 GB VRAM?
Yes. The Q8_0 quant uses about 0.7 GB memory at 8k context, well within an 8 GB VRAM limit.
Does the model support vision tasks?
No. The model is trained only for Python code generation.
What license applies to this model?
The model is released under the Apache‑2.0 license.