GP

gpt2-small-danish

GptGGUF by afridevaUpdated 2023-12-28
Download on Hugging Face
Parameters163M
Context1K
Layers12
Architecturegpt2
Smallest quant0.1 GB
Quick answer

gpt2-small-danish 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 7 quants, from 0.1 GB (Q2_K) to 0.3 GB.

GPT-2 small Danish text generation

A GPT‑2 small model adapted for Danish. It contains 0.163 billion parameters and was trained on the Danish part of the Oscar dataset. The model supports a context length of 1024 tokens.

Good at

  • Danish text generation
  • Low‑parameter inference
  • Fine‑tuning for Danish tasks

Limits

  • No vision support
  • License not specified
  • Context limited to 1024 tokens

Best for

  • Generating Danish short texts
  • Fine‑tuning Danish language models
  • Rapid prototyping with low memory

Who it’s for. Developers needing a lightweight Danish language model for inference or fine‑tuning. The model is suitable for projects that require low GPU memory usage and quick deployment.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.1 GB 0.6 GB
Fits Get file →
Q3_K_M0.1 GB 0.6 GB
Fits Get file →
Q4_K_M0.1 GB 0.6 GB
Fits Get file →
Q5_K_M0.1 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 →
—0.3 GB 0.9 GB
Fits Get file →

For 8 GB VRAM, use Q2_K (0.08 GB file, 0.9 GB memory) or Q3_K_M (0.1 GB file, 0.9 GB memory). For 12 GB VRAM, Q4_K_M (0.11 GB file, 0.9 GB memory) or Q5_K_M (0.12 GB file, 0.9 GB memory) are suitable. Higher quants increase file size and memory slightly.

What GPU do you need for gpt2-small-danish?

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 the main file (0.3 GB file, about 1.1 GB in use).

Which gpt2-small-danish quant should you choose?

Q4_K_M is the usual starting point for gpt2-small-danish: 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 byafrideva
FamilyGpt
Downloads (HF)724
Last updated2023-12-28

Frequently asked questions about gpt2-small-danish

How much VRAM does gpt2-small-danish 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-small-danish on an 8 GB GPU?

Yes, with the smaller files: the 0.3 GB file needs about 1.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of gpt2-small-danish GGUF?

It depends on the quant: Q2_K is 0.1 GB, Q3_K_M is 0.1 GB, Q4_K_M is 0.1 GB, Q5_K_M is 0.1 GB, Q6_K is 0.1 GB, Q8_0 is 0.2 GB and 1 more.

What context length does gpt2-small-danish 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-small-danish GGUF?

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

Can I run this model on 8 GB VRAM?

Yes, the Q2_K and Q3_K_M quantizations use about 0.9 GB memory at 8 k context, fitting within 8 GB VRAM.

Does this model support multilingual text?

No, it is specifically trained for Danish and does not include other languages.

Is the model fine‑tunable?

Yes, the model is pre‑trained and can be fine‑tuned for new tasks.

Similar models

Browse all →

More from afrideva

All by afrideva →

More Gpt models

All Gpt →

Other tiny models

All tiny models →