Qwen2.5-72B-Instruct
Listed in tt-inference-server on 2 hardware types; best status Functional.
In tt-inference-server
| Hardware | Engine and implementation | Status | Context | Users | Build | Support page |
|---|---|---|---|---|---|---|
WH GalaxyGALAXY |
vLLM tt-transformers |
Functional | 128K | 128 | tt-metal 13f44c5vLLM 0edd242Image ghcr.io/tenstorrent/tt-inference-server/vllm-tt-metal-src-release-ubuntu-22.04-amd64:0.3.0-13f44c5-0edd242 |
- |
WH GalaxyGALAXY_T3K |
vLLM tt-transformers |
Functional | 128K | 32 | tt-metal 13f44c5vLLM 0edd242Image ghcr.io/tenstorrent/tt-inference-server/vllm-tt-metal-src-release-ubuntu-22.04-amd64:0.3.0-13f44c5-0edd242 |
- |
WH LoudBox/QuietBoxT3K |
vLLM tt-transformers |
Functional | 128K | 32 | tt-metal 13f44c5vLLM 0edd242Image ghcr.io/tenstorrent/tt-inference-server/vllm-tt-metal-src-release-ubuntu-22.04-amd64:0.3.0-13f44c5-0edd242 |
- |
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
No tt-model bundle has been published for this model.
Details
| Kind | LLM (from tt-inference-server model type) |
| Parameters | 72B |
| Family | Qwen (from the start of the name) |
| Implementation | tt-transformers |
| Disk needed | 164 GB |
| RAM needed | 180 GB |
| Tool-call parser | hermes |
| Listed by | tt-inference-server |