Model Releases

Excited to see Qwen3.8 running at scale with TokenSpeed! 🚀 Light on latency, big on speed. Kudos to LightSeek for the fantastic Day-0 suppo…

Excited to see Qwen3.8 running at scale with TokenSpeed! 🚀 Light on latency, big on speed. Kudos to LightSeek for the fantastic Day-0 support! @lightseekorg We’re proud to be the Day 0 open-source inf

DGX agentx-post
model-releasesqwen--x

Excited to see Qwen3.8 running at scale with TokenSpeed! 🚀 Light on latency, big on speed. Kudos to LightSeek for the fantastic Day-0 support! @lightseekorg We’re proud to be the Day 0 open-source inference engine partner for @Alibaba_Qwen 3.8. To serve this 2.4T-parameter model across multi-node @NVIDIAAI Blackwell inference, we optimized DP/EP scaling across nodes, delivering 30%+ faster performance than TP16, plus DSpark speculati…

Related

Source: Qwen (X) | 2026-08-14

Loading related sources…