Instructions to use mohammadjafari-dev/local-ai-toolkit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries
NeMo
How to use mohammadjafari-dev/local-ai-toolkit with NeMo:
```
# tag did not correspond to a valid NeMo domain.
```
Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use mohammadjafari-dev/local-ai-toolkit 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 mohammadjafari-dev/local-ai-toolkit:UD-Q4_K_XL
# Run inference directly in the terminal:
llama cli -hf mohammadjafari-dev/local-ai-toolkit:UD-Q4_K_XL

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf mohammadjafari-dev/local-ai-toolkit:UD-Q4_K_XL
# Run inference directly in the terminal:
llama cli -hf mohammadjafari-dev/local-ai-toolkit:UD-Q4_K_XL

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 mohammadjafari-dev/local-ai-toolkit:UD-Q4_K_XL
# Run inference directly in the terminal:
./build/bin/llama cli -hf mohammadjafari-dev/local-ai-toolkit:UD-Q4_K_XL

Use Docker

docker model run hf.co/mohammadjafari-dev/local-ai-toolkit:UD-Q4_K_XL

Llama new
LM Studio
Jan

vLLM

How to use mohammadjafari-dev/local-ai-toolkit with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/mohammadjafari-dev/local-ai-toolkit:UD-Q4_K_XL

Ollama
How to use mohammadjafari-dev/local-ai-toolkit with Ollama:
```
ollama run hf.co/mohammadjafari-dev/local-ai-toolkit:UD-Q4_K_XL
```
Unsloth Desktop

How to use mohammadjafari-dev/local-ai-toolkit with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf mohammadjafari-dev/local-ai-toolkit:UD-Q4_K_XL

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": "mohammadjafari-dev/local-ai-toolkit:UD-Q4_K_XL"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use mohammadjafari-dev/local-ai-toolkit with Docker Model Runner:
```
docker model run hf.co/mohammadjafari-dev/local-ai-toolkit:UD-Q4_K_XL
```

Lemonade

How to use mohammadjafari-dev/local-ai-toolkit with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mohammadjafari-dev/local-ai-toolkit:UD-Q4_K_XL

Run and chat with the model

lemonade run user.local-ai-toolkit-UD-Q4_K_XL

List all available models

lemonade list

Hermes Agent

How to use mohammadjafari-dev/local-ai-toolkit with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf mohammadjafari-dev/local-ai-toolkit:UD-Q4_K_XL

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 mohammadjafari-dev/local-ai-toolkit:UD-Q4_K_XL

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use mohammadjafari-dev/local-ai-toolkit with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf mohammadjafari-dev/local-ai-toolkit:UD-Q4_K_XL

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 "mohammadjafari-dev/local-ai-toolkit:UD-Q4_K_XL" \
  --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"

local-ai-toolkit / .gitattributes

Commit History

Jul 18

17:15
⚡ Reorganize local-ai-toolkit: Optimize agents, Gemma, and uncensored folders via safe Copy+Delete

mohammad

Verified signature
9c3bcbf
16:20
Upload 9-Uncensored_Models/Speed/General/Huihui_Qwen3_VL_8B_Uncensored_Q8_0/Huihui-Qwen3-VL-8B-Instruct-abliterated.mmproj-f16.gguf with huggingface_hub

mohammad

Verified signature
f742867
16:17
Upload 9-Uncensored_Models/Quality/General/Huihui_Qwen3.6_35B_Claude4.7_Opus_MTP_Uncensored_Q4_K/mmproj-model-f16.gguf with huggingface_hub

mohammad

Verified signature
f890ebb
15:30
Upload 4-Document_Analysis_and_RAG/gemma-4-12b-it-UD-Q4_K_XL/MTP/mtp-gemma-4-12b-it-Q8_0.gguf with huggingface_hub

mohammad

Verified signature
e40d4fc
15:28
Upload 4-Document_Analysis_and_RAG/gemma-4-12b-it-UD-Q4_K_XL/mmproj-BF16.gguf with huggingface_hub

mohammad

Verified signature
0e9d04c
15:00
Upload 1-Universal_Foundation_LLMs/Speed/Qwen3.5-9B-Q5_K_M/mmproj-BF16.gguf with huggingface_hub

mohammad

Verified signature
6b34348
14:55
Upload 1-Universal_Foundation_LLMs/Quality/Qwen3.6-35B-A3B-UD-Q4_K_XL/mmproj-BF16.gguf with huggingface_hub

mohammad

Verified signature
c6be9dd

Jul 16

15:11
⚡ Clean repository structure: Move files atomically via Copy+Delete

mohammad

Verified signature
94761b8
14:24
Upload folder using huggingface_hub

mohammad

Verified signature
effe02d
14:12
Upload folder using huggingface_hub

mohammad

Verified signature
4c0dc34
13:59
Upload folder using huggingface_hub

mohammad

Verified signature
d4741f3
13:50
Upload folder using huggingface_hub

mohammad

Verified signature
c800a9e
13:44
Upload folder using huggingface_hub

mohammad

Verified signature
88392ba
13:39
Upload folder using huggingface_hub

mohammad

Verified signature
b6d0fc3
13:28
Upload folder using huggingface_hub

mohammad

Verified signature
7a1459d
13:25
Upload folder using huggingface_hub

mohammad

Verified signature
0070075
13:19
Upload folder using huggingface_hub

mohammad

Verified signature
e4ce090
13:07
Upload folder using huggingface_hub

mohammad

Verified signature
cf72142
13:03
Upload folder using huggingface_hub

mohammad

Verified signature
a52a488
12:36
Upload folder using huggingface_hub

mohammad

Verified signature
b63e6e4
12:17
Upload folder using huggingface_hub

mohammad

Verified signature
b91a551
12:16
Upload folder using huggingface_hub

mohammad

Verified signature
a386811
12:13
Upload folder using huggingface_hub

mohammad

Verified signature
fb6d3e9
12:12
Upload folder using huggingface_hub

mohammad

Verified signature
634c827
12:10
Upload folder using huggingface_hub

mohammad

Verified signature
a91a7ba
12:10
Upload folder using huggingface_hub

mohammad

Verified signature
f083928
12:09
Upload folder using huggingface_hub

mohammad

Verified signature
3b73a2c
12:04
Upload folder using huggingface_hub

mohammad

Verified signature
fa9b28f
11:53
Upload folder using huggingface_hub

mohammad

Verified signature
9ce79f7
11:42
Upload folder using huggingface_hub

mohammad

Verified signature
286659d
11:37
Upload folder using huggingface_hub

mohammad

Verified signature
801a298
11:35
Upload folder using huggingface_hub

mohammad

Verified signature
286f0f7
11:23
Upload folder using huggingface_hub

mohammad

Verified signature
93ba96e
11:12
Upload folder using huggingface_hub

mohammad

Verified signature
1a7ac93
11:08
Upload folder using huggingface_hub

mohammad

Verified signature
a35bbf7
10:56
initial commit

mohammad

Verified signature
b8c6a5c

Commit History

Jul 18

⚡ Reorganize local-ai-toolkit: Optimize agents, Gemma, and uncensored folders via safe Copy+Delete

Upload 9-Uncensored_Models/Speed/General/Huihui_Qwen3_VL_8B_Uncensored_Q8_0/Huihui-Qwen3-VL-8B-Instruct-abliterated.mmproj-f16.gguf with huggingface_hub

Upload 9-Uncensored_Models/Quality/General/Huihui_Qwen3.6_35B_Claude4.7_Opus_MTP_Uncensored_Q4_K/mmproj-model-f16.gguf with huggingface_hub

Upload 4-Document_Analysis_and_RAG/gemma-4-12b-it-UD-Q4_K_XL/MTP/mtp-gemma-4-12b-it-Q8_0.gguf with huggingface_hub

Upload 4-Document_Analysis_and_RAG/gemma-4-12b-it-UD-Q4_K_XL/mmproj-BF16.gguf with huggingface_hub

Upload 1-Universal_Foundation_LLMs/Speed/Qwen3.5-9B-Q5_K_M/mmproj-BF16.gguf with huggingface_hub

Upload 1-Universal_Foundation_LLMs/Quality/Qwen3.6-35B-A3B-UD-Q4_K_XL/mmproj-BF16.gguf with huggingface_hub

Jul 16

⚡ Clean repository structure: Move files atomically via Copy+Delete

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Upload folder using huggingface_hub

initial commit