Model reference · open weights

Ming-flash-omni

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

Ming-flash-omni is an open-weight language model from inclusionAI. Ming-flash-omni-Preview (BF16) weighs 209 GB; the smallest configuration that runs it is 2× H200 141 GB.

Request Rent a GPU

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

Ming-flash-omni is an any-to-any multimodal model developed by inclusionAI that accepts image, text, video, and audio inputs to generate image, text, and audio outputs.
The model utilizes a sparse Mixture-of-Experts architecture with 104.4B total parameters, of which 6B are active per token.
It is distributed under the MIT license and supports English.

Summary of the inclusionAI/Ming-flash-omni-Preview model card, 2026-10-01

Hugging Face ↗GitHub ↗Paper ↗

What it is

Released by	inclusionAI
Released	2025-10-14
Parameters	104.4B
VRAM	209 GB for the weights

What it runs on

Memory and cards for Ming-flash-omni-Preview (BF16)

209 GBweights, file size

66 MBcache per 1K tokens

2.9 GBruntime overhead, at least

32,768 tokenscontext max

Card	Requests at once		Context max	Memory
Card	8K each	32K each	Context max	Memory
RTX 3060 12 GB … B200 180 GB 12 smaller cards
2× H200 141 GB tensor parallel	88	22	all 32K	138 GB a card
4× H100 80 GB tensor parallel	120	30	all 32K	78.1 GB a card
4× A100 80 GB tensor parallel	172	43	all 32K	78.2 GB a card
2× B200 180 GB tensor parallel	216	54	all 32K	176 GB a card
4× RTX PRO 6000 Blackwell 96 GB tensor parallel	237	59	all 32K	93.8 GB a card

Memory needed at each load

Requests at once	8K tokens each	32K tokens each
1	212 GB	214 GB
5	214 GB	222 GB
8	216 GB	229 GB
16	220 GB	246 GB
32	229 GB	280 GB
64	246 GB	349 GB

One card, with vLLM's small-card settings.

Details

Type	Language models
Task	Omni (any→any)
Runs with	diffusers
Based on	inclusionAI/Ling-flash-2.0
Popularity	1k downloads / month
Weights	209 GB, Ming-flash-omni-Preview (BF16, file size)

Languages