AxForge
Sign in Get started

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-v1.5-8B (BF16) weighs 18.4 GB; the smallest configuration that runs it is RTX 4090 24 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

Hugging Face ↗

What it is

Released byswiss-ai
Released2026-07-24
Parameters8.9B
VRAM18.4 GB for the weights

What it runs on

Memory and cards for Apertus-v1.5-8B (BF16)

18.4 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.

CardWeights alone
RTX 3060 12 GB … RTX 4060 Ti 16 GB
2 smaller cards		does not fit
RTX 3090 24 GBfits
RTX 4090 24 GBfits
RTX 5090 32 GBfits
L40S 48 GBfits
A100 80 GBfits
H100 80 GBfits
RTX PRO 6000 Blackwell 96 GBfits
DGX Spark (GB10) 128 GB unifiedfits
H200 141 GBfits
B200 180 GBfits

Builds

Sizes, precisions & builds

BuildParamsPrecisionWeightsSmallest setup
Apertus-v1.5-8B (above) ↗ 8.9BBF16 18.4 GBRTX 4090 24 GB
Apertus-v1.5-70B ↗ 72.0BBF16 145 GBB200 180 GB

How it works

How language models work

Your prompttext / messagesTransformerattention over tokensNext-token loopgenerate + streamResponsetext · tool callsA language model reads your tokens and predicts the next one, again and again, streaming the reply back.
© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms