Instructions to use XHToken/Spark-X2.5-4B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use XHToken/Spark-X2.5-4B-GGUF 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 XHToken/Spark-X2.5-4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf XHToken/Spark-X2.5-4B-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf XHToken/Spark-X2.5-4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf XHToken/Spark-X2.5-4B-GGUF: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 XHToken/Spark-X2.5-4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf XHToken/Spark-X2.5-4B-GGUF: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 XHToken/Spark-X2.5-4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf XHToken/Spark-X2.5-4B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/XHToken/Spark-X2.5-4B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use XHToken/Spark-X2.5-4B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "XHToken/Spark-X2.5-4B-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "XHToken/Spark-X2.5-4B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/XHToken/Spark-X2.5-4B-GGUF:Q4_K_M

Ollama
How to use XHToken/Spark-X2.5-4B-GGUF with Ollama:
```
ollama run hf.co/XHToken/Spark-X2.5-4B-GGUF:Q4_K_M
```
Unsloth Desktop

How to use XHToken/Spark-X2.5-4B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf XHToken/Spark-X2.5-4B-GGUF: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": "XHToken/Spark-X2.5-4B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use XHToken/Spark-X2.5-4B-GGUF with Docker Model Runner:
```
docker model run hf.co/XHToken/Spark-X2.5-4B-GGUF:Q4_K_M
```

Lemonade

How to use XHToken/Spark-X2.5-4B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull XHToken/Spark-X2.5-4B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Spark-X2.5-4B-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use XHToken/Spark-X2.5-4B-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf XHToken/Spark-X2.5-4B-GGUF: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 XHToken/Spark-X2.5-4B-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use XHToken/Spark-X2.5-4B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf XHToken/Spark-X2.5-4B-GGUF: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 "XHToken/Spark-X2.5-4B-GGUF: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"

LM Studio: "unknown model architecture: 'spark2_5'" after following build instructions

by MasterLooser - opened 1 day ago

Discussion

MasterLooser

1 day ago

•

edited 1 day ago

Hi, I'm trying to load Spark-X2.5-4B-GGUF in LM Studio following the LM Studio Quick Start instructions on the repo page.

What I did:

Cloned XHToken/llama.cpp, built it with CMake, and copied the output from the bin/debug folder into LM Studio's extensions/backends/cuda12 directory (replacing the existing runtime files)
Downloaded the GGUF model via LM Studio's built-in model downloader (the model is in a separate folder I defined in LM Studio settings, not inside .lmstudio itself)
Opened LM Studio, selected the model, and clicked Load
Error:

Failed to load model.
error loading model: unknown model architecture: 'spark2_5'
My questions:

I'm not sure if copying from bin/debug was correct. should it have been from somewhere else?
I replaced the cuda12 backend, but should it have been a different runtime directory?
Is the spark2_5 architecture name something that needs to be registered, or should the custom llama.cpp build already recognize it?
The GGUF file was downloaded directly through LM Studio's downloader, so it should be intact. Happy to provide more details if needed.

Thanks!

lyang01

SparkLLM org 1 day ago

Could you check whether Runtime Selections in LM Studio is set to the same CUDA 12 runtime whose files you replaced? It may still be using a different runtime.

MasterLooser

about 2 hours ago

i did eventually get it to run by overwritting the CUDA runtime (not CUDA 12) but then i had the problem that it would only load into RAM and completly ignore the vram (even tho gpu offloading was on and maxed out)

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment