models · qwen
image-text-to-text model harvested from Hugging Face (trending). Catalogued at Quarantine — unverified, pending attestation.
| Method | hf-published-sha256 |
|---|
| Publisher | qwen |
|---|---|
| Origin | Recorded as a covered nation under 10 U.S.C. § 4872(f) — the PRC, Russia, Iran or North Korea. The registry did not record which. |
| Licence | apache-2.0 |
| Parameters | 27,781,427,952 (27.8B) |
| Native precision | F8_E4M3 |
| Pulls recorded here | 123,157 |
| Downloads reported upstream | 7,752,562 |
| Hardware | Build measured | Decode @ 8K | Memory @ 8K | Decode mode |
|---|---|---|---|---|
| NVIDIA RTX PRO 6000 Blackwell 96GB | fp8 | 117 tok/s | 95.6 GB | mtp:4 |
| NVIDIA RTX PRO 6000 Blackwell 96GB | fp8 | 105 tok/s | 95.6 GB | mtp |
| NVIDIA RTX 6000 Ada 48GB | fp8 | 64.3 tok/s | 47.0 GB | mtp:4 |
| NVIDIA RTX 6000 Ada 48GB | fp8 | 63.7 tok/s | 47.0 GB | mtp:4 |
| NVIDIA RTX 6000 Ada 48GB | fp8 | 58.0 tok/s | 47.0 GB | mtp |
| NVIDIA DGX Spark 128GB | fp8 | 17.7 tok/s | 111.2 GB | mtp:4 |
| NVIDIA DGX Spark 128GB | fp8 | 17.5 tok/s | 111.3 GB | mtp:4 |
| NVIDIA DGX Spark 128GB | fp8 | 17.0 tok/s | 111.2 GB | mtp |
Measured by local.ai, not by us: 8 runs. Each names its engine pinned by image digest and the exact serve command, in the full record.
Registry record as of 2026-09-01. Identity, licence and parameter count are properties of a release and do not move; tier can, and the verify link above re-checks it against the live registry rather than this page.