Instructions to use abenzerps/Spark-X2.6-4B-Quantized with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use abenzerps/Spark-X2.6-4B-Quantized 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 abenzerps/Spark-X2.6-4B-Quantized:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf abenzerps/Spark-X2.6-4B-Quantized:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf abenzerps/Spark-X2.6-4B-Quantized:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf abenzerps/Spark-X2.6-4B-Quantized: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 abenzerps/Spark-X2.6-4B-Quantized:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf abenzerps/Spark-X2.6-4B-Quantized: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 abenzerps/Spark-X2.6-4B-Quantized:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf abenzerps/Spark-X2.6-4B-Quantized:Q4_K_M

Use Docker

docker model run hf.co/abenzerps/Spark-X2.6-4B-Quantized:Q4_K_M

LM Studio
Jan

vLLM

How to use abenzerps/Spark-X2.6-4B-Quantized with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "abenzerps/Spark-X2.6-4B-Quantized"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "abenzerps/Spark-X2.6-4B-Quantized",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/abenzerps/Spark-X2.6-4B-Quantized:Q4_K_M

Ollama
How to use abenzerps/Spark-X2.6-4B-Quantized with Ollama:
```
ollama run hf.co/abenzerps/Spark-X2.6-4B-Quantized:Q4_K_M
```
Unsloth Desktop

How to use abenzerps/Spark-X2.6-4B-Quantized with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf abenzerps/Spark-X2.6-4B-Quantized: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": "abenzerps/Spark-X2.6-4B-Quantized:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use abenzerps/Spark-X2.6-4B-Quantized with Docker Model Runner:
```
docker model run hf.co/abenzerps/Spark-X2.6-4B-Quantized:Q4_K_M
```

Lemonade

How to use abenzerps/Spark-X2.6-4B-Quantized with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull abenzerps/Spark-X2.6-4B-Quantized:Q4_K_M

Run and chat with the model

lemonade run user.Spark-X2.6-4B-Quantized-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use abenzerps/Spark-X2.6-4B-Quantized with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf abenzerps/Spark-X2.6-4B-Quantized: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 abenzerps/Spark-X2.6-4B-Quantized:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use abenzerps/Spark-X2.6-4B-Quantized with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf abenzerps/Spark-X2.6-4B-Quantized: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 "abenzerps/Spark-X2.6-4B-Quantized: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-X2.6-4B Quantized

GGUF and Safetensors (FP8, NVFP4) quantized variants of XHToken/Spark-X2.6-4B for local execution, agent workflows, and reasoning.

Spark-X2.6-4B by XHToken is a lightweight 4B language model optimized for on-device agents, coding, and tool use. Featuring a hybrid-attention design with up to a 1M context window and controllable thinking budgets (low / high), it matches or outperforms much larger 9B–12B models on standard agent and coding benchmarks while remaining exceptionally fast.

Benchmark

Quantized Files

Quantization	File	Size
FP8	spark-x2.6-4b-fp8.safetensors	4.14 GB
NVFP4	spark-x2.6-4b-NVFP4.safetensors	2.60 GB
BF16	Spark-X2.6-4B-BF16.gguf	7.66 GB
Q8_0	Spark-X2.6-4B-Q8_0.gguf	4.10 GB
Q6_K	Spark-X2.6-4B-Q6_K.gguf	3.20 GB
Q5_K_M	Spark-X2.6-4B-Q5_K_M.gguf	2.80 GB
Q4_K_M	Spark-X2.6-4B-Q4_K_M.gguf	2.47 GB
Q4_0	Spark-X2.6-4B-Q4_0.gguf	2.24 GB

Q4_K_M is recommended for the best balance of size and quality for GGUF. NVFP4 and FP8 offer high performance on supported NVIDIA GPUs.

Usage

1. llama.cpp / llama-server (GGUF)

Interactive Chat via CLI

Run multi-turn interactive conversation directly in your terminal:

./llama-cli -m Spark-X2.6-4B-Q4_K_M.gguf \
    -cnv \
    -c 8192 \
    -n 512 \
    --temp 0.6 \
    -t 8

OpenAI-Compatible API Server

Start llama-server to serve OpenAI-compatible /v1/chat/completions endpoints:

./llama-server -m Spark-X2.6-4B-Q4_K_M.gguf \
    -c 8192 \
    --port 8080

Query via curl:

curl http://localhost:8080/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "messages": [
      {
        "role": "user",
        "content": "Hello! What can you help me with?"
      }
    ],
    "temperature": 0.6
  }'

2. Ollama (GGUF)

Create a Modelfile:

FROM ./Spark-X2.6-4B-Q4_K_M.gguf

TEMPLATE """{{- if .System }}<｜start▁of▁sentence｜><|System|>{{ .System }}
{{ end }}{{- range .Messages }}<｜start▁of▁sentence｜><|{{ if eq .Role "user" }}User{{ else }}Bot{{ end }}|>{{ .Content }}<｜end▁of▁sentence｜>{{- end }}{{- if .Prompt }}<｜start▁of▁sentence｜><|User|>{{ .Prompt }}<｜end▁of▁sentence｜><｜start▁of▁sentence｜><|Bot|><think>
{{ end }}"""

PARAMETER stop "<｜end▁of▁sentence｜>"
PARAMETER stop "<｜start▁of▁sentence｜>"
PARAMETER temperature 0.6

Build and run:

ollama create spark-x2.6 -f Modelfile
ollama run spark-x2.6

3. NVIDIA FP8 & NVFP4 (Safetensors)

Load the quantized weights directly via safetensors for TensorCore-accelerated pipelines (such as comfy-kitchen, vLLM, or custom inference):

import safetensors.torch
import torch

# Load FP8 (torch.float8_e4m3fn with per-tensor scales)
fp8_weights = safetensors.torch.load_file("spark-x2.6-4b-fp8.safetensors")

# Load NVFP4 (packed 4-bit with block-wise scales)
nvfp4_weights = safetensors.torch.load_file("spark-x2.6-4b-NVFP4.safetensors")

Source and Build

Source model: XHToken/Spark-X2.6-4B
Architecture: Spark2_5ForCausalLM (spark2_5 GGUF architecture)
Conversion & Quantization: Upstream llama.cpp & comfy-kitchen
License: Apache 2.0
Checksums: SHA256SUMS

Downloads last month: -

GGUF

Model size

4B params

Architecture

spark2_5

Hardware compatibility

4-bit

5-bit

6-bit

8-bit

16-bit

Model tree for abenzerps/Spark-X2.6-4B-Quantized

Base model

XHToken/Spark-X2.6-4B-Base

Finetuned

XHToken/Spark-X2.6-4B

Quantized

(10)

this model

Collection including abenzerps/Spark-X2.6-4B-Quantized

Spark-X2.6

Collection

Spark-X2.6 model family releases, including GGUF and MLX conversions. • 4 items • Updated about 7 hours ago