Qwen3.8-27B
Listed in tt-inference-server on 1 hardware type; best status Complete. 3 tt-model bundles also published.
In tt-inference-server
| Hardware | Engine and implementation | Status | Context | Users | Build | Support page |
|---|---|---|---|---|---|---|
BH QuietBox 2P300X2 |
vLLM qwen38-27b-qb2 |
Complete | 256K | 16 | tt-metal 978f93bvLLM a723030Image ghcr.io/tenstorrent/tt-inference-server/vllm-tt-metal-src-release-ubuntu-22.04-amd64:0.25.0-978f93b-a723030 |
Open |
Status, context and users are copied from tt-inference-server's release spec (commit 2db98e38c, release 0.25.0). Context is the longest prompt plus reply the entry allows. Users is its highest concurrency. Each row carries its own code link, tt-metal and vLLM commits and image, because they differ between hardware. Nothing on this page is measured.
tt-model bundles
| Bundle | Hardware | Served with | Context | Pushed | |
|---|---|---|---|---|---|
| changh95/qwen3.8-27b-p150x2 | p150x2 | vllm-plugin | - | 2026-10-02 | |
| changh95/qwen3.8-27b-p300x2 | BH QuietBox 2 | vllm-plugin | 256K | 2026-10-02 | |
| tt-hous/qwen3.8-27b | BH 4xP150 | vllm-plugin | 128K | 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 tt-inference-server model type) |
| Parameters | 27B |
| Family | Qwen (from the start of the name) |
| Implementation | qwen38-27b-qb2 |
| Disk needed | 74 GB |
| RAM needed | 67.5 GB |
| Tool-call parser | qwen3_coder |
| Reasoning parser | qwen3 |
| License (bundle cards) | apache-2.0 |
| Listed by | tt-inference-server |