What GPU do I need to run swiss-ai/Apertus-70B-Instruct-2509?
70.6B parameters, published in BF16. View on Hugging Face
Set up Apertus-70B-Instruct-2509Apertus-70B-Instruct-2509 is published by swiss-ai on Hugging Face, with 29,139 downloads and 194 likes to date. It's a ApertusForCausalLM model built for text-generation, published natively in BF16.
VRAM required & cheapest live GPU fit
Required VRAM = weight size at each precision, plus a fixed overhead for KV-cache, activations, and fragmentation. Full formula and assumptions: methodology.
| Precision | Weight size | Required VRAM | Cheapest live fit | GPUs needed | Est. $/hr (full fit) |
|---|---|---|---|---|---|
| BF16 | 131.5 GB | 157.8 GB | RTX A5000 | 7 | $1.23/hr |
| FP8 (quantized) | 65.8 GB | 78.9 GB | RTX PRO 6000 | 1 | $1.38/hr |
| cheaper alt. | RTX 5060 Ti | 5 | $0.550/hr | ||
| INT4 (quantized) | 32.9 GB | 39.5 GB | RTX A6000 | 1 | $0.363/hr |
| cheaper alt. | RTX 5060 Ti | 3 | $0.330/hr |
A GPU is only matched to a row if its hardware supports that precision, and the primary recommendation is always a single-GPU fit when one exists.
INT4 requires a quantized checkpoint actually published for this model, check its Hugging Face page before relying on this row.
Cheapest way to run Apertus-70B-Instruct-2509 at its published (BF16) precision: 7× RTX A5000, at $0.176/hr per GPU ($1.23/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.
Apertus-70B-Instruct-2509: common questions
Can Apertus-70B-Instruct-2509 run on a single GPU?
No. At BF16 it needs 157.8 GB of VRAM, more than a single 32 GB desktop card holds. The cheapest capable card in the live feed is a 24.0 GB RTX A5000, and it takes 7 of them.
How many GPUs do I need to run Apertus-70B-Instruct-2509?
7 at BF16. It needs 157.8 GB of VRAM and the cheapest capable live offer is a 24.0 GB RTX A5000, so 7 of them come to $1.23/hr in total.
Does quantizing Apertus-70B-Instruct-2509 lower the GPU bill?
Yes. At BF16 the cheapest live fit is 7 RTX A5000 cards at $1.23/hr. At INT4 (quantized) it drops to one RTX A6000 at $0.363/hr, provided a quantized checkpoint exists for it.
Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
More Apertus models
- Apertus-8B-Instruct-2509 (8.1B, BF16)
- Apertus-8B-2509 (8.1B, BF16)
Related reading: RTX A5000 pricing and specs, The NVIDIA Inception program, explained, Google Colab alternatives for dedicated GPU access, Free GPU credits for students and researchers, and RunPod volume disk vs. network volume, compared.
