Will this model run on your hardware?
Can I run Apertus-8B-Instruct-2509 locally?
- 8.1B parameters
- context up to 64K
- licence: apache-2.0
- Weights: swiss-ai/Apertus-8B-Instruct-2509 · GGUF: unsloth/Apertus-8B-Instruct-2509-GGUF
Open this page in a browser to check it against your own GPU or Mac: the tool detects your hardware locally and shows the best quantization that fits, the memory it needs and an estimated speed.
Quantizations and file sizes
| Quantization | GGUF file |
|---|---|
| Q8_0 | 8.6 GB |
| Q6_K | 6.6 GB |
| Q5_K_M | 5.8 GB |
| Q4_K_M | 5.1 GB |
| Q3_K_M | 4.2 GB |
| Q2_K | 3.3 GB |
Run it locally
ollama run hf.co/unsloth/Apertus-8B-Instruct-2509-GGUF:Q4_K_M
llama serve -hf unsloth/Apertus-8B-Instruct-2509-GGUF:Q4_K_M
LM Studio: open unsloth/Apertus-8B-Instruct-2509-GGUF