TU

turkish gpt2 large GGUF smashed

TurkishGGUF by PrunaAIUpdated 2026-03-25
Download on Hugging Face
Parameters838M
Context1K
Layers36
Architecturegpt2
Smallest quant0.3 GB
Quick answer

turkish gpt2 large GGUF smashed needs about 2.6 GB of memory at Q4_K_M (a 0.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 14 quants, from 0.3 GB (Q2_K) to 0.9 GB (Q8_0).

Turkish GPT-2 Large compressed in GGUF format

Turkish GPT-2 Large compressed to GGUF format. The model has 0.838B parameters and a trained context of 1024 tokens. It is built on the GPT-2 architecture and is available in multiple quantisations.

Good at

  • Text generation in Turkish
  • Fast inference with low memory
  • Compact model size

Limits

  • No vision support
  • Limited to 1024 token context
  • License not specified

Best for

  • Local Turkish text generation
  • Chatbot prototypes
  • Educational demos

Who it’s for. Developers needing a lightweight Turkish language model for local inference. Researchers testing compressed GPT-2 variants.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.3 GB 1.0 GB
Fits Get file →
Q3_K_S0.4 GB 1.1 GB
Fits Get file →
Q3_K_M0.5 GB 1.1 GB
Fits Get file →
Q3_K_L0.5 GB 1.2 GB
Fits Get file →
Q4_00.5 GB 1.2 GB
Fits Get file →
Q4_K_S0.5 GB 1.2 GB
Fits Get file →
Q4_10.5 GB 1.2 GB
Fits Get file →
Q4_K_M0.5 GB 1.2 GB
Fits Get file →
Q5_00.6 GB 1.3 GB
Fits Get file →
Q5_K_S0.6 GB 1.3 GB
Fits Get file →
Q5_K_M0.6 GB 1.3 GB
Fits Get file →
Q5_10.6 GB 1.3 GB
Fits Get file →
Q6_K0.7 GB 1.4 GB
Fits Get file →
Q8_00.9 GB 1.6 GB
Fits Get file →

For 8GB VRAM, Q4_K_M (0.55GB file, 2.6GB memory at 8k context) is a safe choice. For 4GB VRAM, Q2_K (0.34GB file, 2.4GB memory) fits comfortably. Choose larger quants only if you have more than 8GB VRAM.

What GPU do you need for turkish gpt2 large 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 (0.9 GB file, about 2.9 GB in use).

Which turkish gpt2 large GGUF smashed quant should you choose?

Q4_K_M is the usual starting point for turkish gpt2 large GGUF smashed: it balances file size and quality well. Here it is a 0.5 GB file.

The Q8_0 file is 0.9 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 0.3 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
Parameters838M
Layers36
Trained context1,024 tokens
KV cache (fp16)180 KB per token

Source

Quantized byPrunaAI
FamilyTurkish
Downloads (HF)792
Last updated2026-03-25

Frequently asked questions about turkish gpt2 large GGUF smashed

How much VRAM does turkish gpt2 large GGUF smashed need?

About 2.6 GB at Q4_K_M with an 8K context window. That is the 0.5 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 turkish gpt2 large GGUF smashed on an 8 GB GPU?

Yes, with Q8_0: the 0.9 GB file needs about 2.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of turkish gpt2 large GGUF smashed GGUF?

It depends on the quant: Q2_K is 0.3 GB, Q3_K_S is 0.4 GB, Q3_K_M is 0.5 GB, Q3_K_L is 0.5 GB, Q4_0 is 0.5 GB, Q4_K_S is 0.5 GB and 8 more.

What context length does turkish gpt2 large 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 1.5 GB at 8K and 0.2 GB at 1K.

Where can I download turkish gpt2 large GGUF smashed GGUF?

The files are on Hugging Face in the PrunaAI/turkish-gpt2-large-GGUF-smashed 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 8GB VRAM?

Yes, Q4_K_M requires about 2.6GB memory at 8k context, well below 8GB.

Does it support other languages?

Model is Turkish only; no other languages.

What calibration data was used?

WikiText was used for calibration.

Similar models

Browse all →

More from PrunaAI

All by PrunaAI →

More Turkish models

All Turkish →

Other tiny models

All tiny models →