gpt-oss-120b
Listed in tt-inference-server on 4 hardware types; best status Experimental. 3 tt-model bundles also published.
In tt-inference-server
| Hardware | Engine and implementation | Status | Context | Users | Build | Support page |
|---|---|---|---|---|---|---|
BH GalaxyBLACKHOLE_GALAXY |
vLLM gpt-oss |
Experimental | 128K | 32 | 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 |
BH QuietBox 2P300X2 |
vLLM gpt-oss |
Experimental | 128K | 1 | tt-metal 8c48a10vLLM f52987aImage ghcr.io/tenstorrent/tt-inference-server/vllm-tt-metal-src-release-ubuntu-22.04-amd64:0.17.0-8c48a10-f52987a |
Open |
WH GalaxyGALAXY |
vLLM gpt-oss |
Experimental | 128K | 32 | tt-metal 8c48a10vLLM f52987aImage ghcr.io/tenstorrent/tt-inference-server/vllm-tt-metal-src-release-ubuntu-22.04-amd64:0.17.0-8c48a10-f52987a |
Open |
WH LoudBox/QuietBoxT3K |
vLLM gpt-oss |
Experimental | 16K | 1 | tt-metal 805f43dvLLM a45c614Image ghcr.io/tenstorrent/tt-inference-server/vllm-tt-metal-src-release-ubuntu-22.04-amd64:0.12.0-805f43d-a45c614 |
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/gpt-oss-120b-p150x8 | BH LoudBox | vllm-plugin | 16K | 2026-09-12 | |
| jashansinghTT/gpt-oss-120b-blackhole-fast | BH 4xP150 | vllm-plugin | 128K | 2026-10-16 | |
| tt-hous/gpt-oss-120b | 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 | 120B |
| Family | gpt-oss (from the start of the name) |
| Implementation | gpt-oss |
| Disk needed | 260 GB |
| RAM needed | 300 GB |
| Tool-call parser | openai |
| Reasoning parser | openai_gptoss |
| License (bundle cards) | apache-2.0 |
| Listed by | tt-inference-server |