DictaLM-3.0-24B-Base-FP8

<img src="https://i.ibb.co/5Lbwyr1/dicta-logo.jpg" width="300px"/>

Dicta-LM 3.0: Advancing The Frontier of Hebrew Sovereign LLMs

Dicta-LM 3.0 is a powerful open-weight collection of LLMs, trained on extensive corpora of Hebrew and English texts. The models are available for download and for unlimited use. The models set a new SOTA for their weight-class for Hebrew, both as base models and chat models.

This is the 24-billion-parameter base model, originally initialized from Mistral-Small-3.1-24B-Base-2503.

This version of the model is dynamically quantized to FP8, utilizing the Hopper and Blackwell architectures for faster inference with a lower memory footprint. This quantization of the model can fit on a single L40S GPU.

For full details of this model please read our release blog post or the technical report.

Note: This is not a chat model; rather this is a base model that can be further fine-tuned. Chat model variants are available at the link below.

You can view and access the full collection of base/instruct unquantized/quantized versions of DictaLM 3.0 here.

Usage

vLLM

vllm serve dicta-il/DictaLM-3.0-24B-Base-FP8

If you run out of memory, you can try limiting the context window by setting --max-model-len 8192

Notice

DictaLM-3.0-24-Base-FP8 is a pretrained base model and therefore does not have any moderation mechanisms.

Citation

If you use this model, please cite:

@article{Shmidman2025DictaLM3,
  title={{Dicta-LM 3.0: Advancing The Frontier of Hebrew Sovereign LLMs}},
  author={Shaltiel Shmidman and Avi Shmidman and Amir DN Cohen and Moshe Koppel},
  year={2025},
  publisher={{DICTA / Jerusalem, Israel}},
  note={https://www.dicta.org.il/publications/DictaLM_3_0___Techincal_Report.pdf}
}