Apertus models
3 Apertus models from swiss-ai on Hugging Face, from 8.1B to 70.6B parameters, published by swiss-ai in BF16, with a 64K-token context. The smallest official model, Apertus-8B-2509, needs about 18.0 GB of VRAM at its published precision; the cheapest live fit is RTX A5000 at $0.176/hr.
Pick a size
One row per official Apertus size: the VRAM it needs at each precision, the cheapest GPU that holds it today, and the KV cache for a 32K-token context.
| Model | Parameters | Native VRAM | FP8 VRAM | INT4 VRAM | Live GPU fit (native) | Est. $/hr | KV cache at 32K |
|---|---|---|---|---|---|---|---|
| Apertus-8B-Instruct-2509 | 8.1B | 18.0 GB | 9.0 GB | 4.5 GB | RTX A5000 | $0.176/hr | 4.0 GB |
| Apertus-70B-Instruct-2509 | 70.6B | 158 GB | 78.9 GB | 39.5 GB | AMD MI300X | $2.63/hr | 10.0 GB |
VRAM is weights times a flat 1.2 overhead; the KV cache is a separate per-model figure at 16-bit, shown where the architecture is published. See the methodology.
Official models (3)
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| Apertus-8B-2509 | 8.1B | BF16 | 18.0 GB | RTX A5000 | $0.176/hr |
| Apertus-8B-Instruct-2509 | 8.1B | BF16 | 18.0 GB | RTX A5000 | $0.176/hr |
| Apertus-70B-Instruct-2509 | 70.6B | BF16 | 158 GB | AMD MI300X | $2.63/hr |
VRAM is for the precision the model is published in: the weights times a flat 1.2 overhead, with the KV cache not included. See the methodology. The fit shown is the lowest-priced single GPU type that holds the model at that precision, or the lowest-priced multi-GPU set (up to 8) when none does.