Spark-X2.6-1.7B goes open source: a 1.7B on-device agent model with 1M context and day-0 vLLM support
Spark-X2.6-1.7B is the second Spark-X2.6 model after the 4B, built for on-device use under Apache 2.0. It keeps the Spark-X2.5-1.7B architecture and improves coding, agent, long-context, multilingual and reasoning skills via better post-training, with none/low/high thinking levels. The model card shows SGLang, vLLM, Ollama and other ways to run it, with an example max context of 1,048,576 tokens.
Why it matters
The SparkLLM team open-sourced Spark-X2.6-1.7B, an on-device agent model with native 1M context and adjustable thinking, close to its 4B sibling, with day-0 vLLM and SGLang support.
Sources4
Hugging Face · XHTokenMediaSpark-X2.6-1.7BView original ·
- @vllm_projectX🎉 Spark-X2.6-1.7B from @SparkLLM is out — a compact on-device agent model with 1M native context and controllable thinking (none/low/high), nearly matching its 4B sibling on SWE-Verified and τ²-bench. Day-0 vLLM support via trust-remote-code, incl. vLLM-Ascend for NPU https://twitter.com/SparkLLM/status/2115100695775056057View original · 2 links ·
- @ModelScope2022XSpark-X2.6-1.7B has landed: an open-source 1.7B model built for capable local agents.@SparkLLM 🤖 https://modelscope.ai/collections/XHToken/Spark-X26 🧠 Think only as much as the task needs: Switch between no-thinking, low-thinking, and high-thinking modes to balance answer quality, latency, and inference cost.View original ·
- @sgl_projectXSGLang has Day-0 support for Spark-X2.6-1.7B from @SparkLLM, a compact on-device model that stays close to Spark-X2.6-4B with less than half the parameters. > Stronger coding, agentic, and long-context > Efficient on-device inference, same architecture as Spark-X2.5-1.7B > https://twitter.com/SparkLLM/status/2115100695775056057View original ·
Written by dalao.ai: the title, summary and why it matters are our own words. The original reports are the record; their publishers keep authorship.