Model fiche
Apertus 70B
By Swiss AI · Switzerland
chat
general
multilingual
fr
Overview
A Swiss AI joint effort (EPFL, ETH, CSCS) trained on 15T tokens covering 1000+ languages, including Swiss German and Romansh. Apache 2.0.
When to pick this model
- European data-sovereignty-critical deployments
- Applications serving French, German, Italian, or Romansh users
- Research on broadly multilingual training
- Apache-licensed alternatives to US or Chinese flagships
VRAM requirements by quantization
| Quantization | VRAM required |
|---|---|
| Q4_K_M (recommended) | 40 GB |
| Q5_K_M | 48 GB |
| Q8_0 | 75 GB |
| FP16 (no quantization) | 140 GB |
VRAM figures include model weights plus a typical 8k KV cache and ~600 MB runtime overhead (Ollama / llama.cpp baseline). Add headroom for higher context lengths.
Strengths
- European data sovereignty story
- Only flagship model with native Romansh support
- Apache 2.0 license
- Strong across Alpine and broader European languages
Limitations
- Around 40 GB VRAM at Q4 — multi-GPU required
- Smaller fine-tune ecosystem than Llama or Qwen
- English performance trails best-in-class US models
Architecture & training
Architecture: Dense · 70B · Swiss AI Initiative · European sovereignty
Training: Swiss AI — sovereign European data, strong in FR/DE/IT/RM (Romansh).
Verdict
Europe's most credible sovereign open flagship — pick it when language coverage or data jurisdiction matters more than raw English benchmarks.
Quick start
ollama pull hf.co/swissai/Apertus-70B-GGUFOr use the open-source MCP server to query this model from Claude Desktop, Cursor, or any MCP-compatible client.