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.

ModelParametersNative VRAMFP8 VRAMINT4 VRAMLive GPU fit (native)Est. $/hrKV cache at 32K
Apertus-8B-Instruct-25098.1B18.0 GB9.0 GB4.5 GBRTX A5000$0.176/hr4.0 GB
Apertus-70B-Instruct-250970.6B158 GB78.9 GB39.5 GBAMD MI300X$2.63/hr10.0 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)

ModelParametersPublished asVRAM neededLive GPU fitEst. $/hr
Apertus-8B-25098.1BBF1618.0 GBRTX A5000$0.176/hr
Apertus-8B-Instruct-25098.1BBF1618.0 GBRTX A5000$0.176/hr
Apertus-70B-Instruct-250970.6BBF16158 GBAMD 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.

Start ComfyUI on a rented GPU.

© 2026 Aquanode. All rights reserved.

All trademarks, logos and brand names are the property of their respective owners.