AxForge
Sign in Get started

Model reference · open weights

Ming-Lite-Omni-1.5

LLMs inclusionAI Omni (any→any) 1 build Open weights 1k dl/mo

Ming-Lite-Omni-1.5 is an open-weight language model from inclusionAI. Ming-Lite-Omni-1.5 (BF16) weighs 37.8 GB; the smallest configuration that runs it is L40S 48 GB.

  • Ming-Lite-Omni-1.5 is an any-to-any multimodal model developed by inclusionAI that supports image, video, document, and speech understanding and generation.
  • The model features 18.9B parameters and is built upon the Ling-lite-1.5 architecture.
  • It is released under the MIT license.

Summary of the inclusionAI/Ming-Lite-Omni-1.5 model card, 2026-10-01

Hugging Face ↗GitHub ↗Paper ↗

What it is

Released byinclusionAI
Released2025-07-15
Parameters18.9B
VRAM37.8 GB for the weights

What it runs on

Memory and cards for Ming-Lite-Omni-1.5 (BF16)

37.8 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 5090 32 GB
5 smaller cards		does not fit
L40S 48 GBtight
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