---
license: apache-2.0
pipeline_tag: text-generation
language:
  - en
  - he
tags:
- pretrained
inference:
  parameters:
    temperature: 0.6
---

[<img src="https://i.ibb.co/5Lbwyr1/dicta-logo.jpg" width="300px"/>](https://dicta.org.il)

# 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 our flagship model, a 24-billion-parameter *reasoning* model, originally initialized from [Mistral-Small-3.1-24B-Base-2503](https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Base-2503).

This model is a reasoning chat model, which means that before responding to any given message from the user, the model first thinks out the right way to respond in a designated thinking block. 

This version of the model is quantized to 4-bits (with 16-bit activations), allowing for inference with significantly less memory although with slightly weaker performance. This version of the model can fit on a single 24GB GPU. 

<br/>

&#128640; Try it out in full precision here: [chat.dicta.org.il](https://chat.dicta.org.il)

<br/>

For full details of this model please read our [release blog post](https://dicta.org.il/dicta-lm-3) or the [technical report](https://www.dicta.org.il/publications/DictaLM_3_0___Techincal_Report.pdf).

You can view and access the full collection of base/instruct unquantized/quantized versions of `DictaLM 3.0` [here](https://huggingface.co/collections/dicta-il/dictalm-30-collection).

## Instruction format

In order to leverage instruction fine-tuning, your prompt should be rendered using the chat template specified for this model. Most libraries deal with this automatically, so you can just let them do it. 

## Usage

### vLLM

```bash
vllm serve dicta-il/DictaLM-3.0-24B-Thinking-W4A16 --enable-auto-tool-choice --tool-call-parser hermes --reasoning_parser deepseek_r1
```

> If you run out of memory on a 24GB GPU, decrease the context window and enforce eager: `--max-model-len 8192 --enforce-eager`

And then you can access it via the openai library:

```python
from openai import OpenAI

client = OpenAI(
    base_url="http://localhost:8000/v1",
    api_key="sk-no-key-required"
)

response = client.chat.completions.create(
    model="dicta-il/DictaLM-3.0-24B-Thinking-W4A16",
    messages=[
        {"role": "user", "content": "Hello, how are you?"}
    ],
)

print(response.choices[0].message.content)
```

> The reasoning traces should be available in the response structure in the designated fild. 

The model supports tool-calling, enabling integration with external tools and APIs. For example how to use the tool calling, see the [vLLM documentation](https://docs.vllm.ai/en/stable/features/tool_calling/#tool-calling).

## Citation

If you use this model, please cite:

```bibtex
@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}
}
```