models · internscience
Catalogued from local.ai local-inference benchmark index at Quarantine — unverified, pending attestation.
| Method | hf-published-sha256 |
|---|
| Publisher | internscience |
|---|---|
| Origin | Not recorded. The harvest wrote its own source name into this field, which tells us nothing about jurisdiction. |
| Licence | Apache-2.0 |
| Parameters | 35,107,181,936 (35.1B) |
| Native precision | BF16 |
| Downloads reported upstream | 9,963 |
| Hardware | Build measured | Decode @ 8K | Memory @ 8K | Decode mode |
|---|---|---|---|---|
| NVIDIA RTX PRO 6000 Blackwell 96GB | q4km | 267 tok/s | 27.4 GB | ordinary |
| NVIDIA RTX PRO 6000 Blackwell 96GB | FP8 | 197 tok/s | 90.7 GB | ordinary |
| NVIDIA RTX 6000 Ada 48GB | q4km | 183 tok/s | 27.2 GB | ordinary |
| NVIDIA RTX 6000 Ada 48GB | FP8 | 132 tok/s | 45.0 GB | ordinary |
| MacBook Pro M5 Max 128GB · 40-core GPU | q4km | 114 tok/s | 27.4 GB | ordinary |
| MacBook Pro M4 Max 128GB · 40-core GPU | q4km | 90.8 tok/s | 27.4 GB | ordinary |
| Mac Studio M3 Ultra 96GB · 80-core GPU | q4km | 89.8 tok/s | 27.4 GB | ordinary |
| MacBook Pro M5 Max 128GB · 40-core GPU | 8bit | 86.1 tok/s | 39.3 GB | ordinary |
Measured by local.ai, not by us: 19 runs, 11 more not listed. Each names its engine pinned by image digest and the exact serve command, in the full record.
Registry record as of 2026-09-26. 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.