Instructions to use ngquocvinh/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 ngquocvinh/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 ngquocvinh/Spark-X2.5-4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ngquocvinh/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 ngquocvinh/Spark-X2.5-4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ngquocvinh/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 ngquocvinh/Spark-X2.5-4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf ngquocvinh/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 ngquocvinh/Spark-X2.5-4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ngquocvinh/Spark-X2.5-4B-GGUF:Q4_K_M

Use Docker

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

LM Studio
Jan

vLLM

How to use ngquocvinh/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 "ngquocvinh/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": "ngquocvinh/Spark-X2.5-4B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

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

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

How to use ngquocvinh/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 ngquocvinh/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": "ngquocvinh/Spark-X2.5-4B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

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

Lemonade

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

Pull the model

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

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use ngquocvinh/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 ngquocvinh/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 "ngquocvinh/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"

Spark-X2.5-4B GGUF

Community GGUF quantizations of XHToken/Spark-X2.5-4B.

☕ If you find this GGUF useful, please consider
buying me a coffee.
Your support helps cover the GPU costs of future releases.
Thank you for supporting this work.

About Spark-X2.5-4B

Spark-X2.5-4B is a compact, general-purpose language model developed by SparkLLM. According to the upstream authors, the model is designed for:

General-purpose capabilities: conversation, writing, translation, reasoning, and coding
Tool use and agentic workflows
Native context window of up to 1M tokens
More than 200 supported languages
Efficient hybrid attention: one full-attention layer combined with three sliding-window attention layers
Broad ecosystem support: llama.cpp, vLLM, SGLang, MLX, Ollama, and LM Studio

The upstream model is also designed for broad hardware compatibility and efficient long-context inference.

For the original model architecture, training details, benchmarks, and official usage instructions, see the official model card.

This repository is a quantization-only release for local inference. No model training or fine-tuning was performed.

Files

Quantization	File size (GiB)	A10M generation token/s	Validation	Recommendation / Notes
Q8_0	4.07	67.5	Load/generate pass	High quality; reference quantization.
Q6_K	3.15	79.3	Load/generate pass	High quality; near-reference quality.
Q5_K_M	2.77	87.6	Load/generate pass	Daily use; strong quality/size balance.
Q4_K_M	2.42	92.9	Load/generate pass	Recommended default for general use.
Q3_K_M	2.02	79.9	Load/generate pass	Lower-memory profile; validate your workload.
Q2_K	1.66	95.9	Load/generate pass	Aggressive low-memory profile.
IQ2_XS	1.39	106.8	Load/generate pass	Experimental; validate carefully.
IQ1_M	1.20	39.9	Load/generate pass	Very-low-bit option.
Q1_0	0.76	69.9	Load/generate pass	Experimental / legacy minimum-memory option.

Q1/Q2 can lose instruction following, reasoning, and tool-call reliability. Select based on available memory and validate on the workload that matters to you.

The A10M generation figures were measured with single-stream llama-bench on an NVIDIA A10M.

License and attribution

The upstream model is released under Apache License 2.0. Preserve the upstream attribution and license when redistributing these derivative files. This is a community GGUF quantization, not an official XHToken/SparkLLM release or endorsement.

Checksums are available in SHA256SUMS.txt.

Downloads last month: 1,633

GGUF

Model size

4B params

Architecture

spark2_5

Hardware compatibility

1-bit

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

View +1 variant

Model tree for ngquocvinh/Spark-X2.5-4B-GGUF

Base model

XHToken/Spark-X2.5-4B-Base

Finetuned

XHToken/Spark-X2.5-4B

Quantized

(19)

this model