Instructions to use ZERO-POINT-AI/Miss_MARTHA-9B-Qwen3.5-Omni with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use ZERO-POINT-AI/Miss_MARTHA-9B-Qwen3.5-Omni with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="ZERO-POINT-AI/Miss_MARTHA-9B-Qwen3.5-Omni", filename="martha_9b_v2_F16.gguf", )
llm.create_chat_completion( messages = "No input example has been defined for this model task." )
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use ZERO-POINT-AI/Miss_MARTHA-9B-Qwen3.5-Omni 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 ZERO-POINT-AI/Miss_MARTHA-9B-Qwen3.5-Omni:Q4_K_M_LATEST # Run inference directly in the terminal: llama cli -hf ZERO-POINT-AI/Miss_MARTHA-9B-Qwen3.5-Omni:Q4_K_M_LATEST
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf ZERO-POINT-AI/Miss_MARTHA-9B-Qwen3.5-Omni:Q4_K_M_LATEST # Run inference directly in the terminal: llama cli -hf ZERO-POINT-AI/Miss_MARTHA-9B-Qwen3.5-Omni:Q4_K_M_LATEST
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 ZERO-POINT-AI/Miss_MARTHA-9B-Qwen3.5-Omni:Q4_K_M_LATEST # Run inference directly in the terminal: ./llama-cli -hf ZERO-POINT-AI/Miss_MARTHA-9B-Qwen3.5-Omni:Q4_K_M_LATEST
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 ZERO-POINT-AI/Miss_MARTHA-9B-Qwen3.5-Omni:Q4_K_M_LATEST # Run inference directly in the terminal: ./build/bin/llama-cli -hf ZERO-POINT-AI/Miss_MARTHA-9B-Qwen3.5-Omni:Q4_K_M_LATEST
Use Docker
docker model run hf.co/ZERO-POINT-AI/Miss_MARTHA-9B-Qwen3.5-Omni:Q4_K_M_LATEST
- LM Studio
- Jan
- Ollama
How to use ZERO-POINT-AI/Miss_MARTHA-9B-Qwen3.5-Omni with Ollama:
ollama run hf.co/ZERO-POINT-AI/Miss_MARTHA-9B-Qwen3.5-Omni:Q4_K_M_LATEST
- Unsloth Studio
How to use ZERO-POINT-AI/Miss_MARTHA-9B-Qwen3.5-Omni 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 ZERO-POINT-AI/Miss_MARTHA-9B-Qwen3.5-Omni 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 ZERO-POINT-AI/Miss_MARTHA-9B-Qwen3.5-Omni to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for ZERO-POINT-AI/Miss_MARTHA-9B-Qwen3.5-Omni to start chatting
- Pi
How to use ZERO-POINT-AI/Miss_MARTHA-9B-Qwen3.5-Omni with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf ZERO-POINT-AI/Miss_MARTHA-9B-Qwen3.5-Omni:Q4_K_M_LATEST
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": "ZERO-POINT-AI/Miss_MARTHA-9B-Qwen3.5-Omni:Q4_K_M_LATEST" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use ZERO-POINT-AI/Miss_MARTHA-9B-Qwen3.5-Omni with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf ZERO-POINT-AI/Miss_MARTHA-9B-Qwen3.5-Omni:Q4_K_M_LATEST
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 ZERO-POINT-AI/Miss_MARTHA-9B-Qwen3.5-Omni:Q4_K_M_LATEST
Run Hermes
hermes
- Atomic Chat new
- OpenClaw new
How to use ZERO-POINT-AI/Miss_MARTHA-9B-Qwen3.5-Omni with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf ZERO-POINT-AI/Miss_MARTHA-9B-Qwen3.5-Omni:Q4_K_M_LATEST
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 "ZERO-POINT-AI/Miss_MARTHA-9B-Qwen3.5-Omni:Q4_K_M_LATEST" \ --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 ZERO-POINT-AI/Miss_MARTHA-9B-Qwen3.5-Omni with Docker Model Runner:
docker model run hf.co/ZERO-POINT-AI/Miss_MARTHA-9B-Qwen3.5-Omni:Q4_K_M_LATEST
- Lemonade
How to use ZERO-POINT-AI/Miss_MARTHA-9B-Qwen3.5-Omni with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull ZERO-POINT-AI/Miss_MARTHA-9B-Qwen3.5-Omni:Q4_K_M_LATEST
Run and chat with the model
lemonade run user.Miss_MARTHA-9B-Qwen3.5-Omni-Q4_K_M_LATEST
List all available models
lemonade list
| ZERO POINT INTELLIGENCE LTD — MODEL LICENSE v2.0 | |
| ============================================================ | |
| Copyright (c) 2026 Zero Point Intelligence Ltd | |
| Company Number: 17112086 (Companies House, Scotland) | |
| Director: J Sinclair | |
| Website: https://zeropointai.uk | |
| Licensing: licensing@zeropointai.uk | |
| General: zero.point.intelligence.ltd@zeropointai.uk | |
| ============================================================ | |
| 1. DEFINITIONS | |
| ============================================================ | |
| "The Model" refers to the model weights, configuration files, | |
| tokenizer files, integrity manifests, and all associated | |
| materials distributed under this license. | |
| "Zero Point Intelligence" / "ZPI" refers to Zero Point | |
| Intelligence Ltd, the publisher and rights holder. | |
| "Derivative Work" refers to any model, application, or service | |
| that incorporates, modifies, fine-tunes, quantizes, distills, | |
| or otherwise builds upon The Model. | |
| "Revenue Threshold" refers to £690,000 GBP in annual gross | |
| revenue generated by any product or service incorporating | |
| The Model or any Derivative Work. | |
| ============================================================ | |
| 2. FREE USE — PERMITTED ACTIVITIES | |
| ============================================================ | |
| You MAY, without charge: | |
| a) Download and use The Model for personal, research, | |
| educational, and evaluation purposes. | |
| b) Fine-tune, quantize, or adapt The Model for your own | |
| projects, provided you comply with this license. | |
| c) Deploy The Model in production for commercial use, | |
| PROVIDED your annual revenue from products or services | |
| incorporating The Model remains BELOW the Revenue | |
| Threshold. | |
| d) Redistribute The Model or Derivative Works, subject | |
| to the Redistribution Rules in Section 4. | |
| ============================================================ | |
| 3. COMMERCIAL LICENSE — REVENUE THRESHOLD | |
| ============================================================ | |
| If your product or service built on The Model generates more | |
| than £690,000 GBP in annual gross revenue, you MUST obtain a | |
| commercial license from Zero Point Intelligence Ltd. | |
| Contact: licensing@zeropointai.uk | |
| Commercial licenses include: | |
| - Priority support and custom model builds | |
| - Extended deployment rights | |
| - Negotiable terms based on use case | |
| ============================================================ | |
| 4. REDISTRIBUTION RULES | |
| ============================================================ | |
| If you redistribute The Model or any Derivative Work, you MUST: | |
| a) Include this license in full. | |
| b) Provide clear attribution to Zero Point Intelligence Ltd | |
| as the original publisher. | |
| c) Include the integrity manifest (SHA-256 hashes) if | |
| distributing the original weights. | |
| d) Clearly indicate any modifications made to The Model. | |
| e) Not misrepresent the origin of The Model or claim | |
| original authorship of the base weights. | |
| ============================================================ | |
| 5. MODEL WEIGHT INTEGRITY | |
| ============================================================ | |
| You may NOT remove, alter, or obscure the provenance chain, | |
| integrity manifest, SHA-256 hashes, or Zero Point Intelligence | |
| attribution contained in or associated with the distributed | |
| weights. | |
| The integrity manifest exists to verify authenticity and | |
| protect all users from tampered or corrupted weights. | |
| ============================================================ | |
| 6. TRADEMARKS | |
| ============================================================ | |
| The following names are trademarks of Zero Point Intelligence Ltd: | |
| - Zero Point AI / Zero Point Intelligence | |
| - ZPI | |
| - MARTHA | |
| - MARTIN | |
| - JINX / AGENT J.I.N.X / A.J. | |
| You may NOT use these trademarks for marketing, branding, | |
| product names, or model names of Derivative Works without | |
| prior written permission from Zero Point Intelligence Ltd. | |
| You MAY use these names solely for factual attribution | |
| (e.g., "based on MARTIN by Zero Point Intelligence Ltd"). | |
| ============================================================ | |
| 7. PROHIBITED ACTIVITIES | |
| ============================================================ | |
| You may NOT: | |
| a) Use The Model to generate content that violates | |
| applicable laws in your jurisdiction. | |
| b) Use the outputs of The Model to create training datasets | |
| intended to train new foundational or base models | |
| (no model training feedback loops). | |
| c) Extract or reconstruct the model weights by querying | |
| an API, hosted service, or derivative deployment | |
| (no reverse engineering). | |
| d) Remove this license or attribution from any distribution. | |
| e) Use The Model in any weapon system, mass surveillance | |
| system, or system designed to cause physical harm. | |
| ============================================================ | |
| 8. UPSTREAM MODEL COMPLIANCE | |
| ============================================================ | |
| This model is a derivative of Google's Gemma model family. | |
| Users must comply with the upstream Gemma license terms | |
| (Apache 2.0) in addition to this license. | |
| Where this license and the upstream license conflict, | |
| the more restrictive term applies. | |
| ============================================================ | |
| 9. SAFETY AND RESPONSIBILITY | |
| ============================================================ | |
| You are solely responsible for ensuring your deployment | |
| complies with all local laws, regulations, and safety | |
| requirements in your jurisdiction. | |
| Zero Point Intelligence Ltd assumes no liability for any | |
| misuse, harm, or damages arising from the use of The Model | |
| or any Derivative Work. | |
| The Model is provided for general-purpose use. It has not | |
| been certified for medical, legal, financial, or safety- | |
| critical applications. | |
| ============================================================ | |
| 10. NO WARRANTY | |
| ============================================================ | |
| THE MODEL IS PROVIDED "AS IS" WITHOUT WARRANTY OF ANY KIND, | |
| EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO WARRANTIES | |
| OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE, OR | |
| NON-INFRINGEMENT. | |
| ============================================================ | |
| 11. GOVERNING LAW | |
| ============================================================ | |
| This license shall be governed by and construed in accordance | |
| with the laws of Scotland. Any disputes shall be subject to | |
| the exclusive jurisdiction of the Scottish courts. | |
| ============================================================ | |
| 12. CONTACT | |
| ============================================================ | |
| Commercial licensing: licensing@zeropointai.uk | |
| General enquiries: zero.point.intelligence.ltd@zeropointai.uk | |
| Website: https://zeropointai.uk | |
| HuggingFace: https://huggingface.co/Zero-Point-AI | |
| ============================================================ | |
| Zero Point Intelligence Ltd | |
| Dundee, Scotland | |
| April 2026 | |
| "Technical literacy is freedom." | |