Leaderboard / Swiss AI Initiative (Apertus)
Apertus 1.5 70B
Swiss AI Initiative (Apertus) · Apertus · released 2026-07-24 · data checked 2026-11-03 Needs verification
Apertus 1.5 70B is a 72B-parameter dense model from Swiss AI Initiative (Apertus) (Europe), released 2026-07-24 under the Apache-2.0 license. It doesn't have enough reported benchmarks for an index score yet. It needs about 48.8 GB of memory at 4-bit with an 8K-token context.
Largest fully open European model. Results for 1.5 are only published as charts so far; the scores shown are for the first release, measured by the EuroLLM team.
Benchmarks
Each bar shows this model's score. The tick marks the best large model on that benchmark.
No benchmark results for this release yet. Know of one? Send it.
Earlier version: Apertus 70B Instruct (2509, the first release) Earlier version
Published for the previous release, not this one. Shown for context only: they don't count toward the index or appear in tables. Measured by another lab. Source: huggingface.co, arxiv.org.
Specifications
- Lab
- Swiss AI Initiative (Apertus) (CH · Europe)
- Architecture
- Dense transformer
- Total parameters
- 72B
- Active parameters
- All (dense)
- Size class
- Large
- Context window
- 262K tokens
- Input modalities
- text, image, audio
- Reasoning
- Hybrid (thinking on/off)
- License
- Apache-2.0
- Openness
- Fully open: weights, training data and code
- Memory to run
- ~48.8 GB at 4-bit, 8K context (more sizes)
- Hugging Face
- 8.4K downloads (30 days) · 139 likes
Compare with
- Apertus 1.5 70B vs DeepSeek-R1-Distill-Llama-70B (70.6B, index 50.1)
- Apertus 1.5 70B vs Llama 3.3 70B (70.6B, index 40.8)
- Apertus 1.5 70B vs Nemotron 3.5 Bolt 74B-A9B (74B, index 73.3)
Sources
Something wrong here? Report it.
Run it locally
No GGUF build from a well-known publisher yet.
vllm serve swiss-ai/Apertus-v1.5-70BMemory needed: weights, context cache and runtime buffers (context cache estimated: attention layout not published).
| Quantization | 4K context | 32K context | 256K context |
|---|---|---|---|
| 16-bit F16 | 148 GB | 159 GB | 248 GB |
| 8-bit Q8_0 | 80 GB | 91 GB | 181 GB |
| 4-bit Q4_K_M | 47 GB | 58 GB | 148 GB |