# Spark-X2.6-4B: stronger on-device agents, coding and controllable thinking

> Source: <https://dev.to/sparkllm/spark-x26-4b-stronger-on-device-agents-coding-and-controllable-thinking-2fh>
> Published: 2026-10-20 18:36:52+00:00

Spark-X2.6-4B is here: our latest compact, general-purpose language model for on-device agents and real-world tasks.

It keeps the architecture of Spark-X2.5-4B and improves capabilities through post-training, with gains in coding, agent workflows, long-context tasks, multilingual use and reasoning.

The release focuses on tool use, multi-step planning and software engineering. Selected results from our published evaluation:

| Benchmark | Spark-X2.6-4B | Spark-X2.5-4B | 
|---|---|---|
| BFCL-V4 | 71.8 | 65.1 | 
| MCP-Atlas | 62.4 | 54.6 | 
| BrowseComp | 53.1 | 40.9 | 
| SWE Pro | 54.3 | 44.4 | 
| SWE Verified | 62.8 | 41.6 | 
| AA-LCRv1.1 | 67.3 | 64.7 | 

The full comparison includes similarly sized models and larger 9B and 12B models. Spark-X2.6-4B leads on several listed tasks; rankings vary by benchmark.

These are the release team's reported results. The table evaluates Spark-X2.6-4B with thinking set to **high**. Asterisks identify comparison scores taken from public model cards or papers; dashes mean scores are unavailable. The original footnotes are preserved in the image.

Three thinking levels—**none, low and high**—let applications balance reasoning effort, latency and inference cost. Use the model card's configuration guidance for the selected runtime.

The inference chart reports prefill and decode throughput on **RTX 4090** and **Mac M5 Pro (16-core)** across context lengths. It labels each runtime and quantization setting, including llama.cpp Q4_K_M and Spark INT4 runs using TensorRT or MLX. Compare the relevant hardware, runtime and context length when choosing a deployment.

| Platform | Download | Description | 
|---|---|---|
| Hugging Face | [Spark-X2.6 in Huggingface](https://huggingface.co/collections/XHToken/spark-x26) | Official Hugging Face model collection for Spark-X2.6 | 
| ModelScope | [Spark-X2.6 in ModelScope](https://www.modelscope.cn/collections/XHToken/Spark-X26) | Recommended download source for users in China | 
| Ollama | [Spark-X2.6 in Ollama](https://ollama.com/SparkLLM/Spark-X2.6-4B) | Download and run the model locally with Ollama | 

Direct model weights and model card: [https://huggingface.co/XHToken/Spark-X2.6-4B](https://huggingface.co/XHToken/Spark-X2.6-4B).

With Ollama installed, run:

```
ollama run SparkLLM/Spark-X2.6-4B
```

The release documentation also covers Transformers, SGLang, vLLM, MLX and llama.cpp. Follow the runtime-specific setup in the [model card](https://huggingface.co/XHToken/Spark-X2.6-4B) for required versions, images, plugins and hardware configuration.

The model is released under Apache 2.0. Try it on a coding task or tool-use workflow and share your runtime, hardware and results with the SparkLLM community.