other
0.4B parameters
Restricted
Reviewed November 2026

VBART Large (Turkish Summarization)

Turkish BART-style sequence-to-sequence model fine-tuned specifically for summarization. Not a chat model — purpose-built for input-document → Turkish-summary pipelines.

License: CC-BY-NC-SA-4.0·Context: 1,024 tokens

Overview

Turkish BART-style sequence-to-sequence model fine-tuned specifically for summarization. Not a chat model — purpose-built for input-document → Turkish-summary pipelines.

Strengths

  • Purpose-built for Turkish summarization — output quality beats general models at the task
  • Tiny footprint — runs on CPU or 2GB VRAM

Weaknesses

  • Encoder-decoder architecture — not a drop-in for Ollama/llama.cpp
  • Single-task model; can't be repurposed for chat
  • 1024-token input window limits summarization to short articles
  • CC BY-NC-SA 4.0 license: non-commercial use only

Quantization variants

Each quantization trades model quality for file size and VRAM. Q4_K_M is the most popular starting point.

QuantizationFile sizeVRAM required
F321.6 GB2 GB

Get the model

HuggingFace

Original weights

huggingface.co/vngrs-ai/VBART-Large-Summarization

Source repository — direct quantization required.

Hardware that runs this

Cards with enough VRAM for at least one quantization of VBART Large (Turkish Summarization).

Compare alternatives

Models worth comparing

Same parameter band, plus what's one tier above and below — so you can decide what actually fits your hardware.

Step up
More capable — bigger memory footprint
Step down
Smaller — faster, runs on weaker hardware
No verdicted models in the next tier down yet.

Frequently asked

What's the minimum VRAM to run VBART Large (Turkish Summarization)?

2GB of VRAM is enough to run VBART Large (Turkish Summarization) at the F32 quantization (file size 1.6 GB). Higher-quality quantizations need more.

Can I use VBART Large (Turkish Summarization) commercially?

VBART Large (Turkish Summarization) is released under the CC-BY-NC-SA-4.0, which has restrictions for commercial use. Review the license terms before using it in a product.

What's the context length of VBART Large (Turkish Summarization)?

VBART Large (Turkish Summarization) supports a context window of 1,024 tokens (about 1K).

Source: huggingface.co/vngrs-ai/VBART-Large-Summarization

Reviewed by RunLocalAI Editorial. See our editorial policy for how we research and verify model claims.

Related — keep moving

Before you buy

Verify VBART Large (Turkish Summarization) runs on your specific hardware before committing money.