Llama-3.2-3B-Instruct
Listed in tt-inference-server on 3 hardware types; best status Functional. 1 tt-model bundle also published.
In tt-inference-server
| Hardware | Engine and implementation | Status | Context | Users | Build | Support page |
|---|---|---|---|---|---|---|
WH LoudBox/QuietBoxT3K |
vLLM tt-transformers |
Functional | 128K | 32 | tt-metal 20edc39vLLM 03cb300Image ghcr.io/tenstorrent/tt-inference-server/vllm-tt-metal-src-release-ubuntu-22.04-amd64:0.3.0-20edc39-03cb300 |
- |
n150N150 |
vLLM tt-transformers |
Functional | 128K | 32 | tt-metal 20edc39vLLM 03cb300Image ghcr.io/tenstorrent/tt-inference-server/vllm-tt-metal-src-release-ubuntu-22.04-amd64:0.3.0-20edc39-03cb300 |
- |
n300N300 |
vLLM tt-transformers |
Functional | 128K | 32 | tt-metal 20edc39vLLM 03cb300Image ghcr.io/tenstorrent/tt-inference-server/vllm-tt-metal-src-release-ubuntu-22.04-amd64:0.3.0-20edc39-03cb300 |
- |
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 | |
|---|---|---|---|---|---|
| stisiTT/llama-3.2-3b-blackhole-v51 | p100, p150 | vllm-plugin | 16K | 2026-10-21 |
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 | 3B |
| Family | Llama (from the start of the name) |
| Implementation | tt-transformers |
| Disk needed | 26 GB |
| RAM needed | 7.5 GB |
| Tool-call parser | llama3_json |
| License (bundle cards) | llama3.2 |
| Listed by | tt-inference-server |