GP

gpt2 GGUF smashed

GptGGUF by PrunaAIUpdated 2026-03-25
Download on Hugging Face
Parameters163M
Context1K
Layers12
Architecturegpt2
Smallest quant0.1 GB
Quick answer

gpt2 GGUF smashed needs about 0.9 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 14 quants, from 0.1 GB (Q2_K) to 0.2 GB (Q8_0).

GPT-2 GGUF smashed – 124M parameter model in multiple quantisations

This is a GGUF version of the smallest GPT‑2 model with 124 million parameters. It is available in a range of quantisations from Q2_K to Q8_0. The model is trained on English text for causal language modelling and can be used for text generation or fine‑tuning.

Good at

  • Text generation from prompts
  • Lightweight inference on modest hardware
  • Compatibility with llama.cpp and other GGUF runtimes

Limits

  • No vision or multimodal support
  • Context limited to 1024 tokens
  • MIT license – no commercial restrictions

Best for

  • Quick prototyping of language models
  • Running on edge devices with limited VRAM
  • Educational demonstrations of transformer behaviour

Who it’s for. Developers and researchers who need a small, fast GPT‑2 variant for experimentation or deployment on devices with limited memory. The model is suitable for those who prefer open‑source, MIT‑licensed models.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.1 GB 0.6 GB
Fits Get file →
Q3_K_S0.1 GB 0.6 GB
Fits Get file →
Q3_K_M0.1 GB 0.6 GB
Fits Get file →
Q3_K_L0.1 GB 0.6 GB
Fits Get file →
Q4_00.1 GB 0.6 GB
Fits Get file →
Q4_K_S0.1 GB 0.6 GB
Fits Get file →
Q4_K_M0.1 GB 0.7 GB
Fits Get file →
Q4_10.1 GB 0.7 GB
Fits Get file →
Q5_00.1 GB 0.7 GB
Fits Get file →
Q5_K_S0.1 GB 0.7 GB
Fits Get file →
Q5_K_M0.1 GB 0.7 GB
Fits Get file →
Q5_10.1 GB 0.7 GB
Fits Get file →
Q6_K0.1 GB 0.7 GB
Fits Get file →
Q8_00.2 GB 0.7 GB
Fits Get file →

For 8 GB VRAM, Q4_K_M or Q4_K_S (0.11 GB file, ~0.9 GB VRAM) is recommended. If 4 GB VRAM is available, use Q2_K (0.08 GB file, ~0.9 GB VRAM). For the smallest memory footprint, Q2_K is the best choice. All estimates are approximate.

What GPU do you need for gpt2 GGUF smashed?

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 Q8_0 (0.2 GB file, about 1.0 GB in use).

Which gpt2 GGUF smashed quant should you choose?

Q4_K_M is the usual starting point for gpt2 GGUF smashed: it balances file size and quality well. Here it is a 0.1 GB file.

The Q8_0 file is 0.2 GB, about 1.6 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 Q2_K at 0.1 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegpt2
Parameters163M
Layers12
Trained context1,024 tokens
KV cache (fp16)36 KB per token

Source

Quantized byPrunaAI
FamilyGpt
Licensemit
Downloads (HF)3,387
Last updated2026-03-25

Frequently asked questions about gpt2 GGUF smashed

How much VRAM does gpt2 GGUF smashed need?

About 0.9 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 gpt2 GGUF smashed on an 8 GB GPU?

Yes, with Q8_0: the 0.2 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 gpt2 GGUF smashed GGUF?

It depends on the quant: Q2_K is 0.1 GB, Q3_K_S is 0.1 GB, Q3_K_M is 0.1 GB, Q3_K_L is 0.1 GB, Q4_0 is 0.1 GB, Q4_K_S is 0.1 GB and 8 more.

What context length does gpt2 GGUF smashed support?

The GGUF header lists a trained context length of 1,024 tokens (1K). The KV cache grows with the context you use: about 0.3 GB at 8K and 0.0 GB at 1K.

Where can I download gpt2 GGUF smashed GGUF?

The files are on Hugging Face in the PrunaAI/gpt2-GGUF-smashed repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does gpt2 GGUF smashed use?

Hugging Face lists the license as mit. 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 this model on 4 GB VRAM?

Yes, the Q2_K quantisation uses about 0.9 GB VRAM at 8k context, which fits within a 4 GB budget.

Does this model support image inputs?

No, GPT‑2 is a text‑only model and has no vision capabilities.

What is the maximum context length?

The model was trained with a context of 1024 tokens and supports up to that length.

Other GGUFs of gpt2

Similar models

Browse all →

More from PrunaAI

All by PrunaAI →

More Gpt models

All Gpt →

Other tiny models

All tiny models →