Instructions to use CMSManhattan/JiRackUltra_32b 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/JiRackUltra_32b 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/JiRackUltra_32b:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf CMSManhattan/JiRackUltra_32b: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/JiRackUltra_32b:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf CMSManhattan/JiRackUltra_32b: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 CMSManhattan/JiRackUltra_32b:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf CMSManhattan/JiRackUltra_32b: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 CMSManhattan/JiRackUltra_32b:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf CMSManhattan/JiRackUltra_32b:Q4_K_M

Use Docker

docker model run hf.co/CMSManhattan/JiRackUltra_32b:Q4_K_M

LM Studio
Jan

vLLM

How to use CMSManhattan/JiRackUltra_32b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CMSManhattan/JiRackUltra_32b"
# 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/JiRackUltra_32b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/CMSManhattan/JiRackUltra_32b:Q4_K_M

Ollama
How to use CMSManhattan/JiRackUltra_32b with Ollama:
```
ollama run hf.co/CMSManhattan/JiRackUltra_32b:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use CMSManhattan/JiRackUltra_32b with Docker Model Runner:
```
docker model run hf.co/CMSManhattan/JiRackUltra_32b:Q4_K_M
```

Lemonade

How to use CMSManhattan/JiRackUltra_32b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull CMSManhattan/JiRackUltra_32b:Q4_K_M

Run and chat with the model

lemonade run user.JiRackUltra_32b-Q4_K_M

List all available models

lemonade list

Atomic Chat

kgrabko commited on Aug 3

Commit

537010f

verified ·

1 Parent(s): a4b4af2

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -0

README.md CHANGED Viewed

@@ -47,6 +47,7 @@ A fast and efficient 32B model optimized for CPU inference. The model was refact
 | `cmsmanhattan/jirack-ultra-32b-cpu-q2:latest` | Q2_K | ~13.1 GB | ~14–20 GB | Maximum compression |
 ## Quick Start
 ### Run with Docker
 **Default CPU (Q4 recommended)**
 ```bash
 docker run -d \

 | `cmsmanhattan/jirack-ultra-32b-cpu-q2:latest` | Q2_K | ~13.1 GB | ~14–20 GB | Maximum compression |
 ## Quick Start
 ### Run with Docker
+- 32 B docker can be provided by request .
 **Default CPU (Q4 recommended)**
 ```bash
 docker run -d \