Model reference · open weights

Apertus

LLMs swiss-ai Vision + text 2 builds Open weights 14k dl/mo

Apertus is an open-weight language model from swiss-ai. Apertus-v1.5-70B (BF16) weighs 145 GB; the smallest configuration that runs it is B200 180 GB.

Apertus v1.5 is an 8.9B parameter multimodal language model developed by swiss-ai that accepts image, audio, and text inputs to generate text.
The model supports a context length of up to 262,144 tokens and is designed for multilingual tasks with a thinking mode for reasoning.
It is released under the Apache 2.0 license.

Summary of the swiss-ai/Apertus-v1.5-8B model card, 2026-10-01. The estimate below is for another build of the family.

Hugging Face ↗

What it is

Released by	swiss-ai
Released	2026-07-24
Parameters	8.9B
VRAM	145 GB for the weights

What it runs on

Memory and cards for Apertus-v1.5-70B (BF16)

145 GBweights, file size

762 MBruntime overhead, at least

How much memory each request adds isn't estimated yet for this architecture. The weights need at least the cards below, plus room for the context.

Card	Weights alone
RTX 3060 12 GB … H200 141 GB 11 smaller cards	does not fit
B200 180 GB	tight
8× H100 80 GB tensor parallel	does not fit
8× A100 80 GB tensor parallel	does not fit
8× H200 141 GB tensor parallel	does not fit

Builds

Sizes, precisions & builds

Build	Params	Precision	Weights	Smallest setup
Apertus-v1.5-8B ↗	8.9B	BF16	18.4 GB	RTX 4090 24 GB
Apertus-v1.5-70B (above) ↗	72.0B	BF16	145 GB	B200 180 GB

How it works

How language models work

Details

Type	Language models
Task	Vision + text
Runs with	transformers
Popularity	14k downloads / month
Weights	145 GB, Apertus-v1.5-70B (BF16, file size)