GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
glossAPI
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
glossAPI
Model Tree
swiss-ai/Apertus-8B-2509
Input Modalities
Output Modalities
Supported Functionality
79% Modern Greek, 20% foreign replay, 1% Old Greek. Extended vocabulary: 148,992 tokens. 18 training checkpoints and two checkpoint averages. main: terminal checkpoint.
base-avg30B-50B: GreekMMLU 56.78% (best single checkpoint: 56.81%). Apertus pretraining-suite macro: 64.58% (terminal: 62.95%).
| Resource | Links |
|---|---|
| Original Apertus | Repository, Revision |
| Instruction models | Repository, Stage 1, Greek maths, Conversation |
| Greek base | base-avg30B-50B, 17-step18284-tokens77B, base-avg30B-50B, CHECKPOINTS.md, checkpoint-index.json |
| Pre-training data | Repository, Revision |
| SFT data | Stage 1, Repository |
| Post-training data | Greek maths, Conversation, Repository |
| Tokenizer | Revision, Repository |
| Benchmark audit | Repository |
This work was implemented thanks to a grant by Swiss AI for compute on CSCS.
Collection: Greek Apertus 8B.