---
title: zml/llmd 20261023.0
link: https://zml.ai/posts/llmd-20261023.0/
source: zml-ai
published: 2026-10-22T07:00:00Z
updated: 2026-10-22T07:00:00Z
first_seen: 2026-10-23T18:40:08.262074691Z
summary: 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. And so 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 model series to zml/llmd. We have tested it on NVIDIA and AMD GPU, the only ones we got access to that could host the official release. Google is still telling us there are no TPUs available.
content: extracted
html: 2026-10-22-zml-llmd-20261023-0.html
remote_preview:
  url: https://zml.ai/og/background_hu_32943cbdd2e1726c.png
  alt: zml/llmd 20261023.0 — More speed, more models, more fun.
---

[Back to posts](https://zml.ai/posts/)

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.

And so 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, the only ones we got access to that could host the official release. Google is still telling us there are no TPUs available.

Decode throughput, Qwen/Qwen3.8-Flash-Next, bs=16, zml/llmd 20261023.0 (tok/s)

## 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.

Decode throughput, XiaomiMiMo/MiMo-V2.6-Flash-MOPD, bs=16, zml/llmd 20261023.0 (tok/s)

## 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.

Token Generation, deepseek-ai/DeepSeek-V4.1-Flash, bs=1, 4xGB300 (tok/s)

## Try it today

**NVIDIA**

```bash
docker run -p 8000:8000 --shm-size=256GB --gpus=all -e HF_TOKEN -it zmlai/llmd:cuda \
    --model=hf://Qwen/Qwen3.8-Flash-Next
```

**AMD**

```bash
docker run -p 8000:8000 --shm-size=256GB --device=/dev/kfd --device=/dev/dri -e HF_TOKEN -it zmlai/llmd:rocm \
    --model=hf://Qwen/Qwen3.8-Flash-Next
```

**Intel**

```bash
docker run -p 8000:8000 --device=/dev/dri -e HF_TOKEN -it zmlai/llmd:oneapi \
    --model=hf://Qwen/Qwen3.8-27B
```

**Google TPU**

```bash
docker run --net=host --privileged -e HF_TOKEN -it zmlai/llmd:tpu \
    --model=hf://Qwen/Qwen3.8-27B
```

**Apple Metal**

```bash
brew install zml/zml/llmd
llmd --model=hf://nvidia/Qwen3.8-27B-NVFP4 --batch-size=1
```