AxForge
Sign in Get started

Model reference · open weights

solar-pro-pretrained

LLMs upstage Text gen 1 build Licence not stated 0 dl/mo

solar-pro-pretrained is an open-weight language model from upstage. solar-pro-preview-pretrained (BF16) weighs 44.3 GB; the smallest configuration that runs it is H100 80 GB.

Request Rent a GPU

For self-hosting, compare this build's requirements below with the GPU you plan to rent.

  • solar-pro-pretrained is a 22.1B parameter text-generation model developed by Upstage.
  • It supports English and is intended for fine-tuning for chat purposes.
  • The model card provides usage examples for loading the model and a specific chat template for multi-turn interactions.

Summary of the upstage/solar-pro-preview-pretrained model card, 2026-10-01

Hugging Face ↗

What it is

Released byupstage
Released2024-08-29
Parameters22.1B
VRAM44.3 GB for the weights

What it runs on

Memory and cards for solar-pro-preview-pretrained (BF16)

44.3 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 GBfits
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