zml/llmd 20261023.0

ZML released zml/llmd 20261023.0 on October 22, 2026, adding the Qwen/Qwen3.8-Flash-Next and XiaomiMiMo/MiMo-V2.6 model series to its inference and serving stack and speeding up DeepSeek-V4.1-Flash. ZML said it tested Qwen3.8-Flash-Next on NVIDIA and AMD GPUs, the only hardware it had access to that could host the official releases, because Google reported no TPUs available. The release follows the minor zml/llmd 20261015.0 update, which focused on performance.

Article zml/llmd 20261023.0 More speed, more models, more fun. October 22, 2026 inference / serving / NVIDIA / AMD / TPU / Metal / Intel We are pleased to announce the release of zml/llmd 20261023.0 . While last week’s release zml/llmd 20261015.0 was a minor release with a focus on performance, this week’s release builds on the gains we made and brings more speed, more models, and more fun. This week, we bring new model series to zml/llmd. Qwen/Qwen3.8-Flash-Next This release brings the Qwen/Qwen3.8-Flash-Next series https://huggingface.co/collections/Qwen/qwen38-flash-next model series to zml/llmd. We have tested it on NVIDIA and AMD GPU, which were the only ones we got access to that could host the official releases since Google is still telling us there are no TPUs available. XiaomiMiMo/MiMo-V2.6 This release brings the XiaomiMiMo/MiMo-V2.6 series https://huggingface.co/collections/XiaomiMiMo/mimo-v26 in both RL and MOPD flavour. Faster DeepSeek-V4.1-Flash The hill climb continues. We improved a number of fundamental building blocks and thus DeepSeek-V4.1-Flash got faster. Try it today NVIDIA AMD Intel Google TPU Apple Metal