gpt-oss-20b
gpt-oss-20b, OpenAI's 21B-parameter mixture-of-experts reasoning model (3.6B active parameters), served with vLLM for chat, reasoning and function calling.
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 | |
|---|---|---|---|---|---|
| changh95/gpt-oss-20b-p150x8 | BH LoudBox | vllm-plugin | 32K | 2026-09-12 | |
| jashansinghTT/cohost-llm-blackhole | BH 4xP150 | cohost | - | 2026-10-19 | |
| jashansinghTT/gpt-oss-20b-blackhole-fast | p150, p150x2, BH 4xP150 | vllm-plugin | 128K | 2026-10-19 | |
| tt-hous/gpt-oss-20b | p150, p150x2, 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 the task tag on the bundle's card) |
| Family | gpt-oss (from the start of the name) |
| Tool-call parser | openai |
| Reasoning parser | openai_gptoss |
| Licenses (bundle cards) | apache-2.0, per-model |
| Listed by | tt-model bundle |