Article
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.
This release brings the Qwen/Qwen3.8-Flash-Next series 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.
This release brings the XiaomiMiMo/MiMo-V2.6 series in both RL and MOPD flavour.
The hill climb continues. We improved a number of fundamental building blocks and thus DeepSeek-V4.1-Flash got faster.
NVIDIA
AMD
Intel
Google TPU
Apple Metal