Instructions to use m15dg/local-ai-toolkit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use m15dg/local-ai-toolkit with NeMo:

# tag did not correspond to a valid NeMo domain.

llama-cpp-python

How to use m15dg/local-ai-toolkit with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="m15dg/local-ai-toolkit",
	filename="1-Universal_Foundation_LLMs/Quality/Qwen3.6-35B-A3B-UD-Q4_K_XL/Qwen3.6-35B-A3B-UD-Q4_K_XL.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use m15dg/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 m15dg/local-ai-toolkit:UD-Q4_K_XL
# Run inference directly in the terminal:
llama cli -hf m15dg/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 m15dg/local-ai-toolkit:UD-Q4_K_XL
# Run inference directly in the terminal:
llama cli -hf m15dg/local-ai-toolkit:UD-Q4_K_XL

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 m15dg/local-ai-toolkit:UD-Q4_K_XL
# Run inference directly in the terminal:
./llama-cli -hf m15dg/local-ai-toolkit:UD-Q4_K_XL

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 m15dg/local-ai-toolkit:UD-Q4_K_XL
# Run inference directly in the terminal:
./build/bin/llama-cli -hf m15dg/local-ai-toolkit:UD-Q4_K_XL

Use Docker

docker model run hf.co/m15dg/local-ai-toolkit:UD-Q4_K_XL

LM Studio
Jan

vLLM

How to use m15dg/local-ai-toolkit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "m15dg/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": "m15dg/local-ai-toolkit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/m15dg/local-ai-toolkit:UD-Q4_K_XL

Ollama
How to use m15dg/local-ai-toolkit with Ollama:
```
ollama run hf.co/m15dg/local-ai-toolkit:UD-Q4_K_XL
```

Unsloth Studio

How to use m15dg/local-ai-toolkit 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 m15dg/local-ai-toolkit 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 m15dg/local-ai-toolkit to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for m15dg/local-ai-toolkit to start chatting

How to use m15dg/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 m15dg/local-ai-toolkit:UD-Q4_K_XL

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": "m15dg/local-ai-toolkit:UD-Q4_K_XL"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use m15dg/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 m15dg/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 m15dg/local-ai-toolkit:UD-Q4_K_XL

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use m15dg/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 m15dg/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 "m15dg/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"

Docker Model Runner
How to use m15dg/local-ai-toolkit with Docker Model Runner:
```
docker model run hf.co/m15dg/local-ai-toolkit:UD-Q4_K_XL
```

Lemonade

How to use m15dg/local-ai-toolkit with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull m15dg/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

@@ -96,3 +96,18 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 4-Document_Analysis_and_RAG/gemma-4-12b-it-UD-Q4_K_XL/MTP/mtp-gemma-4-12b-it-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
 9-Uncensored_Models/Quality/General/Huihui_Qwen3.6_35B_Claude4.7_Opus_MTP_Uncensored_Q4_K/mmproj-model-f16.gguf filter=lfs diff=lfs merge=lfs -text
 9-Uncensored_Models/Speed/General/Huihui_Qwen3_VL_8B_Uncensored_Q8_0/Huihui-Qwen3-VL-8B-Instruct-abliterated.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text

 4-Document_Analysis_and_RAG/gemma-4-12b-it-UD-Q4_K_XL/MTP/mtp-gemma-4-12b-it-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
 9-Uncensored_Models/Quality/General/Huihui_Qwen3.6_35B_Claude4.7_Opus_MTP_Uncensored_Q4_K/mmproj-model-f16.gguf filter=lfs diff=lfs merge=lfs -text
 9-Uncensored_Models/Speed/General/Huihui_Qwen3_VL_8B_Uncensored_Q8_0/Huihui-Qwen3-VL-8B-Instruct-abliterated.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text
+3-Agent_Orchestration_and_Routing/1-Orchestrators_and_Managers/GLM-4.7-Flash-UD-Q4_K_XL/GLM-4.7-Flash-UD-Q4_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
+4-Document_Analysis_and_RAG/5-LLM_Generators/gemma-4-12b-it-UD-Q4_K_XL/MTP/mtp-gemma-4-12b-it-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+4-Document_Analysis_and_RAG/5-LLM_Generators/gemma-4-12b-it-UD-Q4_K_XL/gemma-4-12b-it-UD-Q4_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
+4-Document_Analysis_and_RAG/5-LLM_Generators/gemma-4-12b-it-UD-Q4_K_XL/mmproj-BF16.gguf filter=lfs diff=lfs merge=lfs -text
+3-Agent_Orchestration_and_Routing/2-Agentic_Workers/Gemma4_12B_Agentic_Worker_v2/Gemma4_12B_Agentic_Worker_v2.gguf filter=lfs diff=lfs merge=lfs -text
+3-Agent_Orchestration_and_Routing/1-Orchestrators_and_Managers/Agents_A1_35B_MoE_Calibrated_CEO/Agents-A1-IQ4_XS-imatrix-gguf-fable5-calibrated.gguf filter=lfs diff=lfs merge=lfs -text
+3-Agent_Orchestration_and_Routing/3-Guardrails_and_Safety/Llama_Guard_3_8B_i1_Firewall/Llama-Guard-3-8B.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+3-Agent_Orchestration_and_Routing/1-Orchestrators_and_Managers/Hermes_4_3_36B_Quality_Orchestrator/hermes-4_3_36b-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+3-Agent_Orchestration_and_Routing/3-Guardrails_and_Safety/Hermes_4_14B_Speed_Guardrail/Hermes-4-14B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+8-Uncensored_Models/Quality/Code/Huihui_Qwen3_VL_30B_Uncensored_Q4_K_M/Huihui-Qwen3-VL-30B-A3B-Instruct-abliterated.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+8-Uncensored_Models/Quality/General/Huihui_Qwen3.6_35B_Claude4.7_Opus_MTP_Uncensored_Q4_K/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated-ggml-model-Q4_K.gguf filter=lfs diff=lfs merge=lfs -text
+8-Uncensored_Models/Quality/General/Huihui_Qwen3.6_35B_Claude4.7_Opus_MTP_Uncensored_Q4_K/mmproj-model-f16.gguf filter=lfs diff=lfs merge=lfs -text
+8-Uncensored_Models/Speed/Code/Huihui_Qwen3_Coder_30B_Uncensored_i1_Q3_K_M/Huihui-Qwen3-Coder-30B-A3B-Instruct-abliterated.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+8-Uncensored_Models/Speed/General/Huihui_Qwen3_VL_8B_Uncensored_Q8_0/Huihui-Qwen3-VL-8B-Instruct-abliterated.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+8-Uncensored_Models/Speed/General/Huihui_Qwen3_VL_8B_Uncensored_Q8_0/Huihui-Qwen3-VL-8B-Instruct-abliterated.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text

m15dg
/

local-ai-toolkit

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