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

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

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

Miss_MARTHA-9B-Qwen3.5-Omni / integrity_manifest.json

𝒥.S𝐼NCLA𝐼R🇿🇪Ʀ🇴PO𝐼NT-🅰🅸

FIXED — dual-hash tensor proof, both hashes compared

2b13eed verified 4 months ago

Raw

History Blame Contribute Delete

1.34 kB

	{
	"model": "MARTHA-9B-Qwen3.5-Omni",
	"publisher": "Zero Point Intelligence Ltd",
	"base_model": "Qwen/Qwen3.5-9B",
	"license": "Apache-2.0",
	"method": "ghost_pass_1e-6_bfloat16",
	"proof_type": "tensor_level_sha256",
	"proof_note": "First 5 sorted tensors, 8KB each, cast to float32. Different shard counts between MARTHA and base \u2014 tensor-level comparison used.",
	"martha_file": "model.safetensors",
	"martha_tensor_hash": "f5dad9a9c3c5f5f3c4b9f467c86eac3b7b7a7b5236a7bbaf4b3ca629331bd5b6",
	"martha_tensors_sampled": [
	"lm_head.weight",
	"model.language_model.embed_tokens.weight",
	"model.language_model.layers.0.input_layernorm.weight",
	"model.language_model.layers.0.linear_attn.A_log",
	"model.language_model.layers.0.linear_attn.conv1d.weight"
	],
	"base_file": "model.safetensors-00001-of-00004.safetensors",
	"base_tensor_hash": "9b60062e5b713088e867cf7643f68513e126ad8fc7ffe794f592c28b8b45fb6b",
	"base_tensors_sampled": [
	"lm_head.weight",
	"model.language_model.embed_tokens.weight",
	"model.language_model.layers.14.mlp.down_proj.weight",
	"model.language_model.layers.14.mlp.gate_proj.weight",
	"model.language_model.layers.14.mlp.up_proj.weight"
	],
	"weights_unique": true,
	"verification": "pip install safetensors torch; download both files; compare tensor values."
	}