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

Libraries

How to use XHToken/Spark-X2.6-4B with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="XHToken/Spark-X2.6-4B", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("XHToken/Spark-X2.6-4B", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

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

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "XHToken/Spark-X2.6-4B"
# 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-X2.6-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/XHToken/Spark-X2.6-4B

SGLang

How to use XHToken/Spark-X2.6-4B with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "XHToken/Spark-X2.6-4B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "XHToken/Spark-X2.6-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "XHToken/Spark-X2.6-4B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "XHToken/Spark-X2.6-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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

Spark-X2.6 4B: community local API serving smoke report

#31

by Raullen - opened 2 days ago

Discussion

Raullen

2 days ago

Alongside your Spark-MLX-LLM instructions, sharing a community HTTP-serving integration for Spark-X2.6 4B. The measured conversion is abenzerps/Spark-X2.6-4B-MLX-4bit@253181296bd0c643880b0f64daa0049a42148d4a, served using Rapid-MLX's spark-x2.6-4b-4bit alias.

The 2026-10-25 run used an M4 Pro 48 GiB, macOS 26.5.1, Python 3.12.15, MLX 0.32.4, mlx-lm 0.31.3 and mlx-vlm 0.7.2. The report also records a 2026-10-26 repeat on an M3 Ultra 256 GiB.

English/Chinese chat, structured weather tools and thinking on/off passed the recorded probes. Important client detail: this backend coalesced the short SSE answer into one content delta plus usage/end events. Accepting stream=true therefore should not be described as demonstrated token-by-token delivery. The path used the installed spark2_5 implementation, without opting into repository Python execution.

The short tests do not validate the million-token context configuration shown in your deployment guide or reproduce your reasoning-effort benchmarks. The report includes the exact pins and launch command for a narrowly scoped community example.

Evidence and reproduction details: checked-in qualification report. These are historical results, not a new inference run or an upstream endorsement.

Disclosure: I maintain Rapid-MLX; this contribution was prepared with AI assistance under my direction. Anonymous usage-metadata telemetry is enabled by default; DO_NOT_TRACK=1 disables it. Model and conversion licenses still apply.

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