Instructions to use dicta-il/DictaLM-3.0-1.7B-Thinking-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use dicta-il/DictaLM-3.0-1.7B-Thinking-GGUF with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf dicta-il/DictaLM-3.0-1.7B-Thinking-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf dicta-il/DictaLM-3.0-1.7B-Thinking-GGUF:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf dicta-il/DictaLM-3.0-1.7B-Thinking-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf dicta-il/DictaLM-3.0-1.7B-Thinking-GGUF:Q4_K_M
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf dicta-il/DictaLM-3.0-1.7B-Thinking-GGUF:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf dicta-il/DictaLM-3.0-1.7B-Thinking-GGUF:Q4_K_M
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf dicta-il/DictaLM-3.0-1.7B-Thinking-GGUF:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf dicta-il/DictaLM-3.0-1.7B-Thinking-GGUF:Q4_K_M
Use Docker
docker model run hf.co/dicta-il/DictaLM-3.0-1.7B-Thinking-GGUF:Q4_K_M
- LM Studio
- Jan
- vLLM
How to use dicta-il/DictaLM-3.0-1.7B-Thinking-GGUF with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "dicta-il/DictaLM-3.0-1.7B-Thinking-GGUF" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "dicta-il/DictaLM-3.0-1.7B-Thinking-GGUF", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/dicta-il/DictaLM-3.0-1.7B-Thinking-GGUF:Q4_K_M
- Ollama
How to use dicta-il/DictaLM-3.0-1.7B-Thinking-GGUF with Ollama:
ollama run hf.co/dicta-il/DictaLM-3.0-1.7B-Thinking-GGUF:Q4_K_M
- Unsloth Studio
How to use dicta-il/DictaLM-3.0-1.7B-Thinking-GGUF with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for dicta-il/DictaLM-3.0-1.7B-Thinking-GGUF to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for dicta-il/DictaLM-3.0-1.7B-Thinking-GGUF to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for dicta-il/DictaLM-3.0-1.7B-Thinking-GGUF to start chatting
- Pi
How to use dicta-il/DictaLM-3.0-1.7B-Thinking-GGUF with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf dicta-il/DictaLM-3.0-1.7B-Thinking-GGUF:Q4_K_M
Configure the model in Pi
# Install Pi: npm install -g @mariozechner/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "dicta-il/DictaLM-3.0-1.7B-Thinking-GGUF:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use dicta-il/DictaLM-3.0-1.7B-Thinking-GGUF with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf dicta-il/DictaLM-3.0-1.7B-Thinking-GGUF:Q4_K_M
Configure Hermes
# Install Hermes: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash hermes setup # Point Hermes at the local server: hermes config set model.provider custom hermes config set model.base_url http://127.0.0.1:8080/v1 hermes config set model.default dicta-il/DictaLM-3.0-1.7B-Thinking-GGUF:Q4_K_M
Run Hermes
hermes
- Atomic Chat new
- OpenClaw new
How to use dicta-il/DictaLM-3.0-1.7B-Thinking-GGUF with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf dicta-il/DictaLM-3.0-1.7B-Thinking-GGUF:Q4_K_M
Configure OpenClaw
# Install OpenClaw: npm install -g openclaw@latest # Register the local server and set it as the default model: openclaw onboard --non-interactive --mode local \ --auth-choice custom-api-key \ --custom-base-url http://127.0.0.1:8080/v1 \ --custom-model-id "dicta-il/DictaLM-3.0-1.7B-Thinking-GGUF:Q4_K_M" \ --custom-provider-id llama-cpp \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
Run OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"
- Docker Model Runner
How to use dicta-il/DictaLM-3.0-1.7B-Thinking-GGUF with Docker Model Runner:
docker model run hf.co/dicta-il/DictaLM-3.0-1.7B-Thinking-GGUF:Q4_K_M
- Lemonade
How to use dicta-il/DictaLM-3.0-1.7B-Thinking-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull dicta-il/DictaLM-3.0-1.7B-Thinking-GGUF:Q4_K_M
Run and chat with the model
lemonade run user.DictaLM-3.0-1.7B-Thinking-GGUF-Q4_K_M
List all available models
lemonade list
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 1.7-billion-parameter reasoning model, with full precision (BF16), originally initialized from Qwen3-1.7B-Base.
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.
For full details of this model please read our release blog post or the technical report.
You can view and access the full collection of base/instruct unquantized/quantized versions of DictaLM 3.0 here.
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
We recommend using vLLM, but you can use Transformers as well:
Transformers
from transformers import pipeline
generator = pipeline('text-generation', model="dicta-il/DictaLM-3.0-1.7B-Thinking")
messages = [
{"role": "user", "content": "ΧΧΧΧ Χ¨ΧΧΧ ΧΧΧΧ Χ’ΧΧΧ?"},
{"role": "assistant", "content": "ΧΧΧ, ΧΧ Χ ΧΧ ΧΧΧΧ ΧΧΧ ΧΧΧ€ΧΧͺ ΧΧΧ₯ ΧΧΧΧΧ Χ‘ΧΧΧ ΧΧ¨Χ. ΧΧ ΧΧΧ‘ΧΧ£ ΧΧΧΧΧ§ ΧΧͺ ΧΧΧΧΧͺ ΧΧ ΧΧΧ Χ Χ©Χ ΧΧ’Χ ΧΧΧ¦ΧΧ₯ ΧΧΧ ΧΧ Χ©ΧΧ Χ ΧΧΧ©Χ ΧΧΧΧΧ!"},
{"role": "user", "content": "ΧΧΧ ΧΧ© ΧΧ ΧΧͺΧΧΧ ΧΧ ΧΧΧΧΧ Χ?"}
]
print(generator(messages)[0]['generated_text'][-1]) # just print the last message
# 'role': 'assistant', 'content': 'ΧΧΧ©ΧͺΧΧ© Χ©ΧΧΧ: "ΧΧΧ ΧΧ© ΧΧ ΧΧͺΧΧΧ ΧΧ ΧΧΧΧΧ Χ?" ΧΧ ΧΧ Χ Χ¦Χ¨ΧΧΧΧ ΧΧ‘Χ€Χ§ ΧΧͺΧΧΧ ΧΧ ΧΧΧΧΧ Χ. ΧΧ‘Χ€Χ§ ΧΧͺΧΧΧ ΧΧ ΧΧ¨ΧΧ¨ΧΧ, ΧΧΧΧ Χ’Χ Χ©ΧΧΧΧ. ΧΧ‘Χ€Χ§ ΧΧΧ ΧΧ¨Χ‘ΧΧΧͺ. Χ¦Χ¨ΧΧ ΧΧΧΧΧͺ ΧΧΧΧΧΧͺΧ.</think>ΧΧΧΧΧ! ΧΧ Χ ΧΧΧ ΧΧͺΧΧΧ ΧΧ Χ§ΧΧΧ, ΧΧ’ΧΧΧΧ ΧΧΧΧΧ Χ Χ©ΧͺΧΧΧ ΧΧ Χ‘ΧΧͺ. ΧΧΧ¨ ΧΧͺ ΧΧ Χ©ΧΧͺΧΧΧ ΧΧΧ€ΧΧΧ ΧΧΧΧΧ Χ©ΧΧ, ΧΧΧ¨ΧΧΧ© ΧΧΧ€Χ©Χ ΧΧΧͺΧΧΧ ΧΧͺ ΧΧ’ΧΧ¦ΧΧ Χ©Χ ΧΧΧ¨ΧΧ€ΧΧͺ ΧΧ ΧΧͺΧΧΧΧ ΧΧ€Χ ΧΧΧ’Χ Χ©ΧΧ.\n\n---\n\n## 1. ΧΧΧΧ Χ ΧΧ‘ΧΧ‘Χ (ΧΧͺΧΧΧ ΧΧ‘ΧΧ‘Χ)\n\n**ΧΧ¨ΧΧΧΧΧ**\n- 2 ΧΧΧ‘ΧΧͺ ΧΧΧ (ΧΧ ΧΧ ΧΧΧ ΧΧͺΧΧ§ ΧΧΧ¨)\n- 1 ΧΧΧ¦Χ ΧΧΧΧΧ\n- 1 ΧΧ€ΧΧͺ ΧΧΧ₯ ΧΧΧΧΧ ΧΧ¨Χ\n- 1 ΧΧ€ΧΧͺ ΧΧΧ₯ ΧͺΧ€ΧΧΧΧ ΧΧ¨Χ (ΧΧΧ€Χ¦ΧΧΧ ΧΧ)\n- 1β2 ΧΧ€ΧΧͺ ΧΧ¨ΧΧ ΧΧΧ\'ΧΧ\n- 1β2 ΧΧ€ΧΧͺ ΧΧΧ\n- 1β4 ΧΧ€ΧΧͺ Χ€ΧΧ€Χ Χ©ΧΧΧ¨ ΧΧΧΧ ΧΧ¨Χ\n\n**ΧΧΧ¨ΧΧΧͺ**\n1. **ΧΧΧ Χͺ ΧΧΧΧ¦Χ** β ΧΧ§Χ’Χ¨Χ, ΧΧΧ¨Χ€ΧΧ ΧΧΧ ΧΧΧ¦Χ'}
vLLM
vllm serve dicta-il/DictaLM-3.0-1.7B-Thinking --enable-auto-tool-choice --tool-call-parser hermes --reasoning_parser deepseek_r1
And then you can access it via the openai library:
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-3.0-1.7B-Thinking",
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.
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}
}
- Downloads last month
- 272
4-bit
5-bit
8-bit
16-bit
