Apertus 8B
Apertus 8B is an open-weights language model from ETH Zurich, released September 2, 2025. It has 8.1B parameters (dense). The context window is 64K tokens.
Researchers at EPFL, ETH Zurich and CSCS have developed Apertus, a fully open Large Language Model (LLM) – one of the largest of its kind. As a foundational technology, Apertus enables innovation and strengthens AI expertise across research, society and industry by allowing others to build upon it.
Check it against your own PC →
Can you run Apertus 8B locally?
The smallest common GPU it runs on is 6 GB of VRAM (with 32 GB of RAM): Q6_K, split GPU / CPU, roughly 6 tokens per second. Estimates assume 32 GB of DDR5 RAM, a 16K context and llama.cpp-style GGUF quantization. Enter your exact hardware in the live app.
| GPU memory | Verdict | Best quant | VRAM | RAM | tok/s |
|---|---|---|---|---|---|
| 6 GB VRAM | Runs, slowly | Q6_K (≈ lossless) | 5.2 GB | 4.1 GB | ~6 |
| 8 GB VRAM | Runs on GPU | IQ4_XS (good) | 7.0 GB | – | ~37 |
| 12 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 9.3 GB | – | ~32 |
| 16 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 9.3 GB | – | ~43 |
| 24 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 9.3 GB | – | ~78 |
| 32 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 9.3 GB | – | ~140 |
Ready-made quantizations on Hugging Face: mradermacher/Apertus-8B-2509-i1-GGUF · mradermacher/Apertus-8B-2509-GGUF · Colby/Apertus-8B-tulu-xlam-sft-gguf · Colby/Apertus-8B-tulu-xlam-gguf · Colby/apertus-8b-soc-gguf · Colby/Apertus-8B-openhermes-gguf
Benchmark results
Epoch AI has not published results for Apertus 8B yet. New models are usually evaluated within days to weeks.
Links
Announcement · Hugging Face: swiss-ai/Apertus-8B-2509