vLLM(@vllm_project):🎉 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 deployment.

vLLM

@vllm_project

A high-throughput and memory-efficient inference and serving engine for LLMs. Join to discuss together with the community!

Joined March 2024

37 Following 54.1K Followers

vLLM@vllm_project

2026.10.28 00:04

🎉 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 deployment.

SparkLLM@SparkLLM

2026.10.27 15:17

Spark-X2.6-1.7B: less than half the parameters of our 4B, close on two benchmarks: SWE Verified: 59.8 vs 62.8 τ²-bench: 85.3 vs 86.9 Both at high thinking. Try it & Like on HF! @huggingface @Ollama @ModelScope2022