THE MODEL DIRECTORY

Every listing. A closer look.

2,848 catalog records, ordered by name. Each profile has its own link and shows where the information came from. 718 repeat listings (training checkpoints, adapters, other formats and duplicate cloud entries, each shown on its main model’s page) and listings with no published task, size, or price are left out unless you search for them. Show all 3,566

Models A–Z

Page 32 of 60 · Coverage limits

Xiaomi MiMo · Downloadable

MiMo-7B-SFT

Text generation

Generates text for conversations and writing.

Listed Apr 29, 20257B parameters

Xiaomi MiMo · Downloadable

MiMo-Audio-7B-Base

Capabilities unconfirmed

Hugging Face lists its task as any-to-any (several input and output types). See the model card for supported inputs and setup.

Listed Sep 18, 20257B parameters

Xiaomi MiMo · Downloadable

MiMo-Audio-7B-Instruct

Capabilities unconfirmed

Hugging Face lists its task as any-to-any (several input and output types). See the model card for supported inputs and setup.

Listed Sep 18, 20257B parameters

Xiaomi MiMo · Downloadable

MiMo-Audio-Tokenizer

Capabilities unconfirmed

A specialized research model. See the model card for its intended task and supported setup.

Listed Sep 18, 20251.3B parameters

Xiaomi MiMo · Downloadable

MiMo-Embodied-7B

Vision

Understands text and images and responds in text.

Listed Nov 19, 20257B parameters

Xiaomi MiMo · Downloadable

MiMo-V2-Flash

Text generation

Generates text for conversations and writing.

Listed Dec 16, 2025310B parameters

Xiaomi MiMo · Downloadable

MiMo-V2-Flash-Base

Text generation

Generates text for conversations and writing.

Listed Dec 16, 2025310B parameters

Xiaomi MiMo · Downloadable

MiMo-V2.5

Video understandingText generation

Generates text for conversations and writing.

Listed Apr 27, 2026311B parameters

Xiaomi MiMo · Downloadable

MiMo-V2.5-ASR

TranscriptionAudio understanding

Works with speech or audio. Check the model card for transcription and generation capabilities.

Listed Apr 23, 20267.6B parameters

Xiaomi MiMo · Downloadable

MiMo-V2.5-Base

Video understandingText generation

Generates text for conversations and writing.

Listed Apr 27, 2026311B parameters

Xiaomi MiMo · Downloadable

MiMo-V2.5-DFlash

Text generation

Generates text, according to its published model architecture (MiMoV2ForCausalLM). No task is listed on Hugging Face, so check the model card for intended use.

Listed Jul 3, 2026311B parameters

Xiaomi MiMo · Downloadable

MiMo-V2.5-Pro

Text generation

Generates text for conversations and writing.

Listed Apr 27, 20261T parameters

Xiaomi MiMo · Downloadable

MiMo-V2.5-Pro-Base

Text generation

Generates text for conversations and writing.

Listed Apr 27, 20261T parameters

Xiaomi MiMo · Downloadable

MiMo-V2.5-Pro-FP4-DFlash

Text generation

Generates text for conversations and writing.

Listed Jun 8, 20261T parameters

Xiaomi MiMo · Downloadable

MiMo-V2.6-Distill-Qwen-9B

Vision

Understands text and images and responds in text.

Listed Sep 21, 20269B parameters

Xiaomi MiMo · Downloadable

MiMo-V2.6-Flash-MOPD

Video understandingText generation

Generates text for conversations and writing.

Listed Sep 27, 2026311B parameters

Xiaomi MiMo · Downloadable

MiMo-V2.6-Flash-RL

Video understandingText generation

Generates text for conversations and writing.

Listed Sep 21, 2026311B parameters

Xiaomi MiMo · Downloadable

MiMo-V2.6-Pro-MOPD

Video understandingText generation

Generates text for conversations and writing.

Listed Sep 27, 20261T parameters

Xiaomi MiMo · Downloadable

MiMo-V2.6-Pro-RL

Video understandingText generation

Generates text for conversations and writing.

Listed Sep 21, 20261T parameters

Xiaomi MiMo · Downloadable

MiMo-VL-7B-RL

Vision

Understands text and images and responds in text.

Listed May 30, 20257B parameters

Xiaomi MiMo · Downloadable

MiMo-VL-7B-RL-2508

Vision

Understands text and images and responds in text.

Listed Aug 7, 20257B parameters

Xiaomi MiMo · Downloadable

MiMo-VL-7B-SFT

Vision

Understands text and images and responds in text.

Listed May 30, 20257B parameters

Xiaomi MiMo · Downloadable

MiMo-VL-7B-SFT-2508

Vision

Understands text and images and responds in text.

Listed Aug 7, 20257B parameters

inclusionAI · Downloadable

Ming-3.0-asr-tiny

TranscriptionAudio understanding

Works with speech or audio. Check the model card for transcription and generation capabilities.

Listed Oct 14, 20268.9B parameters

inclusionAI · Downloadable

Ming-3.0-audio-flash

TranscriptionAudio generationEmbeddings

Works with speech or audio. Check the model card for transcription and generation capabilities.

Listed Sep 3, 2026128B parameters

inclusionAI · Downloadable

Ming-3.0-audio-tiny

TranscriptionAudio generationEmbeddings

Works with speech or audio. Check the model card for transcription and generation capabilities.

Listed Sep 3, 20268.9B parameters

inclusionAI · Downloadable

Ming-3.0-tts-0.5B

Audio generation

Works with speech or audio. Check the model card for transcription and generation capabilities.

Listed Sep 22, 2026500M parameters

inclusionAI · Downloadable

Ming-3.0-tts-tiny

Audio generationEmbeddings

Works with speech or audio. Check the model card for transcription and generation capabilities.

Listed Sep 22, 20269B parameters

inclusionAI · Downloadable

Ming-flash-omni-2.0

Capabilities unconfirmed

Hugging Face lists its task as any-to-any (several input and output types). See the model card for supported inputs and setup.

Listed Feb 10, 2026104B parameters

inclusionAI · Downloadable

Ming-flash-omni-Preview

Capabilities unconfirmed

Hugging Face lists its task as any-to-any (several input and output types). See the model card for supported inputs and setup.

Listed Oct 14, 2025104B parameters

inclusionAI · Downloadable

Ming-Image-0.1-Design

Image generation

Creates or edits images. Check the model card for supported inputs and output settings.

Listed Sep 17, 20266.2B parameters

inclusionAI · Downloadable

Ming-Image-0.1-Design-Layer

Capabilities unconfirmed

Creates or edits images. Check the model card for supported inputs and output settings.

Listed Sep 17, 20266.2B parameters

inclusionAI · Downloadable

Ming-Lite-Omni

Capabilities unconfirmed

Hugging Face lists its task as any-to-any (several input and output types). See the model card for supported inputs and setup.

Listed May 2, 202519B parameters

inclusionAI · Downloadable

Ming-Lite-Omni-1.5

Capabilities unconfirmed

Hugging Face lists its task as any-to-any (several input and output types). See the model card for supported inputs and setup.

Listed Jul 15, 202519B parameters

inclusionAI · Downloadable

Ming-Lite-Uni

VisionImage generationImage editing

Understands text and images and responds in text.

Listed May 2, 20251.6B parameters

inclusionAI · Downloadable

Ming-omni-tts-0.5B

Audio generation

Works with speech or audio. Check the model card for transcription and generation capabilities.

Listed Feb 11, 2026500M parameters

inclusionAI · Downloadable

Ming-omni-tts-16.8B-A3B

Audio generation

Works with speech or audio. Check the model card for transcription and generation capabilities.

Listed Feb 11, 202617B parameters

inclusionAI · Downloadable

Ming-omni-tts-tokenizer-12Hz

Audio generation

Works with speech or audio. Check the model card for transcription and generation capabilities.

Listed Feb 11, 2026780M parameters

inclusionAI · Downloadable

Ming-UniAudio-16B-A3B

Capabilities unconfirmed

Hugging Face lists its task as any-to-any (several input and output types). See the model card for supported inputs and setup.

Listed Sep 29, 202516B parameters

inclusionAI · Downloadable

Ming-UniAudio-16B-A3B-Edit

Capabilities unconfirmed

A specialized research model. See the model card for its intended task and supported setup.

Listed Sep 30, 202516B parameters

inclusionAI · Downloadable

Ming-UniVision-16B-A3B

Capabilities unconfirmed

Hugging Face lists its task as any-to-any (several input and output types). See the model card for supported inputs and setup.

Listed Sep 30, 202516B parameters

inclusionAI · Downloadable

MingTok-Audio

Capabilities unconfirmed

A specialized research model. See the model card for its intended task and supported setup.

Listed Sep 29, 20251.4B parameters

inclusionAI · Downloadable

MingTok-Vision

Embeddings

Turns content into numerical representations for semantic search and retrieval.

Listed Sep 30, 2025698M parameters

OpenBMB · Downloadable

MiniCPM-1B-sft

Text generation

Generates text for conversations and writing.

Listed Apr 10, 20241B parameters

OpenBMB · Downloadable

MiniCPM-2B-128k

Text generation

Generates text for conversations and writing.

Listed Apr 9, 20242B parameters

OpenBMB · Downloadable

MiniCPM-2B-dpo

Text generation

Generates text for conversations and writing.

+1 other format

Listed Jan 31, 20242B parameters

OpenBMB · Downloadable

MiniCPM-2B-dpo-bf16-llama-format

Text generation

Generates text for conversations and writing.

Listed Feb 6, 20242B parameters

OpenBMB · Downloadable

MiniCPM-2B-dpo-fp32

Text generation

Generates text for conversations and writing.

Listed Jan 30, 20242B parameters

Listing dates are source catalog dates, not verified public releases. This growing library does not yet cover every released model.