Instructions to use CMSManhattan/JiRackDeltaNet_27b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use CMSManhattan/JiRackDeltaNet_27b 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 CMSManhattan/JiRackDeltaNet_27b:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf CMSManhattan/JiRackDeltaNet_27b:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf CMSManhattan/JiRackDeltaNet_27b:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf CMSManhattan/JiRackDeltaNet_27b:Q4_K_M

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf CMSManhattan/JiRackDeltaNet_27b:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf CMSManhattan/JiRackDeltaNet_27b:Q4_K_M

Use Docker

docker model run hf.co/CMSManhattan/JiRackDeltaNet_27b:Q4_K_M

Llama new
LM Studio
Jan

vLLM

How to use CMSManhattan/JiRackDeltaNet_27b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CMSManhattan/JiRackDeltaNet_27b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CMSManhattan/JiRackDeltaNet_27b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/CMSManhattan/JiRackDeltaNet_27b:Q4_K_M

Ollama
How to use CMSManhattan/JiRackDeltaNet_27b with Ollama:
```
ollama run hf.co/CMSManhattan/JiRackDeltaNet_27b:Q4_K_M
```
Unsloth Desktop

How to use CMSManhattan/JiRackDeltaNet_27b with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf CMSManhattan/JiRackDeltaNet_27b:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "CMSManhattan/JiRackDeltaNet_27b:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use CMSManhattan/JiRackDeltaNet_27b with Docker Model Runner:
```
docker model run hf.co/CMSManhattan/JiRackDeltaNet_27b:Q4_K_M
```

Lemonade

How to use CMSManhattan/JiRackDeltaNet_27b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull CMSManhattan/JiRackDeltaNet_27b:Q4_K_M

Run and chat with the model

lemonade run user.JiRackDeltaNet_27b-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use CMSManhattan/JiRackDeltaNet_27b with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf CMSManhattan/JiRackDeltaNet_27b: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 CMSManhattan/JiRackDeltaNet_27b:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use CMSManhattan/JiRackDeltaNet_27b with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf CMSManhattan/JiRackDeltaNet_27b: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 "CMSManhattan/JiRackDeltaNet_27b: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"

kgrabko commited on Sep 22

Commit

5dd91ae

verified ·

1 Parent(s): ccf187d

Update README.md

Browse files

Files changed (1) hide show

README.md +5 -0

README.md CHANGED Viewed

@@ -40,6 +40,11 @@ license: mit
 - Robotcs, Routing, Coding,  Multimedia, Advanced tool calling via JiRackDeltaNetTokenizer
 - JiRack DeltaNet understand video and images that best for Robotics also
 # JiRack DeltaNet 27B (CPU)
 A fast and efficient 27B model optimized for CPU inference. Built on a Qwen3.8-style DeltaNet architecture (hybrid attention + SSM), with an updated tokenizer that includes **Routing**, **Media**, **Vision**, **Sound**, **Tool call**, and **Robotics** tags. Ready-to-run GGUF quantizations, and native Ollama support with reasoning disabled by default for fast, direct responses.
 - JiRack is a cloud-ready model that helps save money on cloud infrastructure. It can be used as an expert model in RAG deployments, with the ONNX JiRack Java server as an alternative.

 - Robotcs, Routing, Coding,  Multimedia, Advanced tool calling via JiRackDeltaNetTokenizer
 - JiRack DeltaNet understand video and images that best for Robotics also
+## PARTNERSHIP
+- NVIDIA
+- FISERV
 # JiRack DeltaNet 27B (CPU)
 A fast and efficient 27B model optimized for CPU inference. Built on a Qwen3.8-style DeltaNet architecture (hybrid attention + SSM), with an updated tokenizer that includes **Routing**, **Media**, **Vision**, **Sound**, **Tool call**, and **Robotics** tags. Ready-to-run GGUF quantizations, and native Ollama support with reasoning disabled by default for fast, direct responses.
 - JiRack is a cloud-ready model that helps save money on cloud infrastructure. It can be used as an expert model in RAG deployments, with the ONNX JiRack Java server as an alternative.