02 / LANGUAGE MODELS

Leading AI models

Search and browse model details from enabled sources

CONFIGURED MODEL CHANNELS

Discover models across sources.

52393 models
ModelScope.ai · Model

MiniMax-H3-Image

MiniMax/MiniMax-H3-Image

text-to-image-synthesis

text-to-image-synthesistext-to-imageimage-to-imageimage-editingminimax-h3-image-community-license-agreement

Size 33.71B · Downloads 23 · Likes 48

View model details ↗
ModelScope.ai · kimi_k31

Kimi-K3.1-Pro

moonshotai/Kimi-K3.1-Pro

image-text-to-text

image-text-to-textcompressed-tensorsconversationalkimi-k3.1-pro

Size 2.78T · Downloads 49 · Likes 64

View model details ↗
ModelScope.ai · step5_vl

Step-5-Preview

stepfun-ai/Step-5-Preview

text-generation

text-generationother

Size 604.34B · Downloads 434 · Likes 59

View model details ↗
ModelScope.ai · llama

Nanbeige4.3-33B

nanbeige/Nanbeige4.3-33B

text-generation

text-generationllmnanbeigeapache-2.0

Size 33.12B · Downloads 25 · Likes 53

View model details ↗
ModelScope.ai · pro_v

LongCat-2.5

meituan-longcat/LongCat-2.5

image-text-to-text

image-text-to-textmultimodalimage-text-to-texttext-generationmit

Size 1.78T · Downloads 34 · Likes 48

View model details ↗
ModelScope.ai · minimax_m3_vl

MiniMax-M3.1-Flash

MiniMax/MiniMax-M3.1-Flash

image-text-to-text

image-text-to-textmultimodalmoeagentminimax-community

Size 220.49B · Downloads 88 · Likes 64

View model details ↗
ModelScope.ai · Model

Qwen-Image-2.1-Turbo

Qwen/Qwen-Image-2.1-Turbo

text-to-image-synthesis

text-to-image-synthesisqwenimage-generationimage-editingqwen-research

Size 16.22B · Downloads 159 · Likes 62

View model details ↗
ModelScope.ai · qwen4_exp

Qwen3.8-Flash-Next

Qwen/Qwen3.8-Flash-Next

image-text-to-text

image-text-to-textqwen-community-1.0

Size 180.00B · Downloads 255 · Likes 108

View model details ↗
ModelScope.ai · glm_moe_dsa

Atria-Dawn

Shanghai_AI_Laboratory/Atria-Dawn

No description provided

Size 753.33B · Downloads 46 · Likes 50

View model details ↗
ModelScope.ai · qwen3_5

JEV-27B-VL

AutoTrust-Labs/JEV-27B-VL

image-text-to-text

image-text-to-textjevsystem-onesystem-twoapache-2.0

Size 27.78B · Downloads 1714 · Likes 52

View model details ↗
ModelScope.ai · bailing_hybrid

Ling-3.1-flash

inclusionAI/Ling-3.1-flash

text-generation

text-generationmit

Size 572.12B · Downloads 57 · Likes 43

View model details ↗
ModelScope.ai · glm_moe_dsa

Atria-Dawn-Preview

Shanghai_AI_Laboratory/Atria-Dawn-Preview

text-generation

text-generationarxiv:2609.15818mit

Size 753.33B · Downloads 107 · Likes 49

View model details ↗
ModelScope.ai · qwen2_5_vl

TeleOCR

XingChen-AGI/TeleOCR

image-text-to-text

image-text-to-textdocument-parsingocrmultimodal

Size 1.42B · Downloads 68 · Likes 15

View model details ↗
ModelScope.ai · glm_moe_dsa

GLM-5.3

zai-org/GLM-5.3

text-generation

text-generationglm-5.3

Size 753.33B · Downloads 911 · Likes 92

View model details ↗
ModelScope.ai · qwen3_5_moe_text

VoyagerX

Qwen/Qwen3.8-2.4T-A95B

text-generation

text-generationqwen3.8-max

Size 4556.39 GiB · Downloads 112 · Likes 47

View model details ↗
ModelScope.ai · deepseek_v4

DeepSeek-V4-Pro-0813

deepseek-ai/DeepSeek-V4-Pro-0813

No description provided

mit

Size 889.48B · Downloads 141 · Likes 71

View model details ↗
ModelScope.ai · minimax_music3

MiniMax-Music3

MiniMax/MiniMax-Music3

No description provided

music-generationtext-to-musicpytorchsglang-omni

Size 20.97B · Downloads 148 · Likes 37

View model details ↗
ModelScope.ai · Model

Qwen-Image-2.1

Qwen/Qwen-Image-2.1

image-to-image

image-to-imagediffusersqwenimage-generationqwen-research

Size 16.22B · Downloads 529 · Likes 132

View model details ↗
ModelScope.ai · kimi_k3

Kimi-K3

moonshotai/Kimi-K3

image-text-to-text

image-text-to-textcompressed-tensorsconversationalkimi-k3

Size 1.50T · Downloads 242 · Likes 53

View model details ↗
ModelScope.ai · xing4_0

Xing4.0-29B-A4B

XingChen-AGI/Xing4.0-29B-A4B

No description provided

Size 31.22B · Downloads 201 · Likes 16

View model details ↗
ModelScope.ai · Model

MiniMax-H3

MiniMax/MiniMax-H3

No description provided

text-to-videoimage-to-videoimage-text-to-videovideo-to-videominimax-h3-community-license-agreement

Size 240.83B · Downloads 2066 · Likes 49

View model details ↗
ModelScope.ai · qwen3_5_moe

Intern-S2-397B

Shanghai_AI_Laboratory/Intern-S2-397B

image-text-to-text

image-text-to-textapache-2.0

Size 403.42B · Downloads 72 · Likes 7

View model details ↗
ModelScope.ai · Model

IndexTTS-2.5

IndexTeam/IndexTTS-2.5

text-to-speech

text-to-speechtext-to-speechttszero-shotbilibili-model-license

Size 596.05M · Downloads 108 · Likes 26

View model details ↗
ModelScope.ai · Model

Wan2.2-Animate-2-14B

Wan-AI/Wan2.2-Animate-2-14B

text-to-video-synthesis

text-to-video-synthesisapache-2.0

Size 32.79B · Downloads 137 · Likes 26

View model details ↗
ModelScope.ai · glm_moe_dsa

Macaron-V1-Venti

mindlab-research/Macaron-V1-Venti

text-generation

text-generationmacaronmacaron-v1glm-5.2mit

Size 753.33B · Downloads 1822 · Likes 23

View model details ↗
ModelScope.ai · bailing_hybrid

Ling-3.0-flash

inclusionAI/Ling-3.0-flash

text-generation

text-generationmit

Size 127.49B · Downloads 280 · Likes 25

View model details ↗
ModelScope.ai · glm_moe_dsa

GLM-5.2

zai-org/GLM-5.2

text-generation

text-generationmit

Size 753.33B · Downloads 24126 · Likes 92

View model details ↗
ModelScope.ai · nemotron3_diarization

Nemotron-3-Diarization

nv-community/Nemotron-3-Diarization

voice-activity-detection

voice-activity-detectionspeaker-diarizationstreaming-sortformerspeaker-taggingopenmdw-1.1

Size 99.23M · Downloads 70 · Likes 7

View model details ↗
ModelScope.ai · hy_v3

Hy3

Tencent-Hunyuan/Hy3

text-generation

text-generation

Size 298.79B · Downloads 168 · Likes 32

View model details ↗
ModelScope.ai · qwen3_5_moe

KAT-Coder-V2.5-Dev

Kwaipilot/KAT-Coder-V2.5-Dev

text-generation

text-generationcodeagentagentic-codingapache-2.0

Size 34.66B · Downloads 127 · Likes 23

View model details ↗

Search scope follows the enabled model source configuration. Model records are cached locally; verify licenses and files on each source.