AxForge
Sign in Get started

Model reference · open weights

Soofi-S

LLMs Soofi-Project Text gen 1 build Its own licence terms 519 dl/mo

Soofi-S is an open-weight language model from Soofi-Project. Soofi-S-Base (BF16) weighs 63.2 GB; the smallest configuration that runs it is H100 80 GB.

  • Soofi-S-30B-A3B is a 31.6B parameter hybrid Mamba-2 and Mixture-of-Experts base model developed by the SOOFI consortium for text generation.
  • It is a German-English bilingual model with a context length of up to 1M tokens, designed as a foundation for further post-training and research rather than direct end-user deployment.
  • The model is currently a beta preview with an "other" license, though the final version is planned to be released under a permissive license.

Summary of the Soofi-Project/Soofi-S-Base model card, 2026-10-01

Hugging Face ↗Paper ↗

What it is

Released bySoofi-Project
Released2026-07-01
Parameters31.6B
VRAM63.2 GB for the weights

What it runs on

Memory and cards for Soofi-S-Base (BF16)

63.2 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 … L40S 48 GB
6 smaller cards		does not fit
A100 80 GBfits
H100 80 GBtight
RTX PRO 6000 Blackwell 96 GBfits
DGX Spark (GB10) 128 GB unifiedfits
H200 141 GBfits
B200 180 GBfits

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