SM

Smol GPT

SmolGGUF by gggff123Updated 2026-10-12
Download on Hugging Face
Parameters135M
Context8K
Layers30
Architecturellama
Smallest quant0.1 GB
Quick answer

Smol GPT needs about 0.8 GB of memory at Q4_K_M (a 0.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 8 quants, from 0.1 GB (Q4_0) to 0.3 GB (F16).

Smol GPT is a 135M-parameter Smol model in GGUF format, quantized by gggff123. Its trained context length is 8K tokens. The repository has 8 quant files, from 0.1 GB (Q4_0) to 0.3 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_00.1 GB 0.8 GB
Fits Get file →
Q3_K_M0.1 GB 0.8 GB
Fits Get file →
Q4_10.1 GB 0.8 GB
Fits Get file →
Q4_K_M0.1 GB 0.8 GB
Fits Get file →
Q5_K_M0.1 GB 0.8 GB
Fits Get file →
Q6_K0.1 GB 0.8 GB
Fits Get file →
Q8_00.1 GB 0.8 GB
Fits Get file →
F160.3 GB 1.0 GB
Fits Get file →

What GPU do you need for Smol GPT?

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 (0.3 GB file, about 1.0 GB in use).

Which Smol GPT quant should you choose?

Q4_K_M is the usual starting point for Smol GPT: it balances file size and quality well. Here it is a 0.1 GB file.

The Q8_0 file is 0.1 GB, about 1.4 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q4_0 at 0.1 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

Architecturellama
Parameters135M
Layers30
Trained context8,192 tokens
KV cache (fp16)23 KB per token

Source

Quantized bygggff123
FamilySmol
Downloads (HF)328
Last updated2026-10-12

Frequently asked questions about Smol GPT

How much VRAM does Smol GPT need?

About 0.8 GB at Q4_K_M 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 Smol GPT on an 8 GB GPU?

Yes, with F16: the 0.3 GB file needs about 1.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Smol GPT GGUF?

It depends on the quant: Q4_0 is 0.1 GB, Q3_K_M is 0.1 GB, Q4_1 is 0.1 GB, Q4_K_M is 0.1 GB, Q5_K_M is 0.1 GB, Q6_K is 0.1 GB and 2 more.

What context length does Smol GPT support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.2 GB at 8K.

Where can I download Smol GPT GGUF?

The files are on Hugging Face in the gggff123/Smol-GPT 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 →

More from gggff123

All by gggff123 →

More Smol models

All Smol →

Other tiny models

All tiny models →