Qwen3.8-Flash-Next
Qwen3.8-Flash-Next, a mixture-of-experts model with 125B parameters (about 6B active per token) plus a 51B n-gram embedding table, served with vLLM as a text-only chat and completion endpoint with tool calling and separated reasoning…
Community model. It is published as a tt-model bundle and is not in tt-inference-server's release spec. Tenstorrent has not reviewed the model or its bundles. Serve at your own risk.
tt-model bundles
| Bundle | Hardware | Served with | Context | Pushed | |
|---|---|---|---|---|---|
| DeAIafdeling/qwen38-flash-next | BH QuietBox 2 | http-server | 128K | 2026-10-01 | |
| DeAIafdeling/qwen38-flash-next-qb2-256k | BH QuietBox 2 | vllm-plugin | - | 2026-10-04 | |
| changh95/qwen3.8-flash-next-p150x8 | BH LoudBox | tt-dit-server | - | 2026-09-20 | |
| sjettTT/qwen3.8-flash-next_p150x4 | BH 4xP150, BH QuietBox 2 | tt-dit-server | - | 2026-09-29 | |
| tt-hous/qwen3.8-flash-next | BH QuietBox 2 | vllm-plugin | - | 2026-10-29 |
From tt-model search --catalog and each bundle's manifest (tt-model info). A bundle lists every hardware profile its manifest defines. Each bundle is published by its owner, and Tenstorrent has not reviewed it. Serve at your own risk.
Details
| Kind | LLM (from the task tag on the bundle's card) |
| Family | Qwen (from the start of the name) |
| Tool-call parser | qwen3_xml |
| Reasoning parser | qwen3 |
| Licenses (bundle cards) | qwen-community-1.0, qwen-license-apache-2.0 |
| Listed by | tt-model bundle |