Gold Open Source
ExplorePackagesVulnerabilitiesMCP Servers
Login
Gold Open Source

The authoritative source for production-ready open-source components. Every package, container image, AI model, and MCP server undergoes rigorous verification for security, malware, and license compliance.

Explore Gold

  • Explore Everything
  • Packages
  • Gold Packages
  • Container Images
  • AI Models
  • MCP Servers
  • Agent Skills
  • Chip Manufacturers

Security Data & Tools

  • Scan Your Dependencies
  • Trending Threats
  • Threat RSS Feeds
  • CVE Database
  • Actively Exploited (KEV)
  • SGZ Zero-Days
  • CWE Index
  • MITRE ATT&CK
  • Malicious Packages
  • Security Glossary
  • Supply-Chain Report
  • Developers (API & Badge)
  • Chrome Extension
  • Credits & Data Sources

Products

  • The Platform
  • ESSCM
  • Portal
  • TPRM
  • OSM
  • Cowork
  • Code / Runner
  • Guard

Use Cases

  • Know Your Software
  • Auto-Fix Vulnerabilities
  • Asset Discovery
  • AI Governance
  • MCP Server Security
  • Supply Chain Compliance
  • Zero-Day Discovery
  • All Use Cases

Company

  • About
  • Pricing
  • Blog
  • Documentation
  • Safeguard Academy
  • Contact
  • Privacy Policy
  • Terms of Service

© 2026 Gold Open Source. All rights reserved.

Built with care bySafeguard
Home/AI Models
AI & LLM Models

AI Models

475 AI and LLM models — 460 open-weight models (sourced from HuggingFace) plus notable frontier models — with developer, license, and modality.

475 models

OpenAI logoOpenAI logoGPT-4oclosedOpenAI●ProprietaryMultimodal (vision-language)OpenAI logoOpenAI logoGPT-4.1closedOpenAI●ProprietaryText generation / LLMOpenAI logoOpenAI logoo3closedOpenAI●ProprietaryReasoning LLMAnthropic logoAnthropic logoClaude Opus 4closedAnthropic●ProprietaryText generation / LLMAnthropic logoAnthropic logoClaude SonnetclosedAnthropic●ProprietaryText generation / LLMAnthropic logoAnthropic logoClaude HaikuclosedAnthropic●ProprietaryText generation / LLMGoogle logoGemini 2.5 ProclosedGoogle DeepMind●ProprietaryMultimodal (vision-language)Google logoGemini 2.5 FlashclosedGoogle DeepMind●ProprietaryMultimodal (vision-language)xAI logoGrokclosedxAI●ProprietaryText generation / LLMMistral AI logoMistral LargeclosedMistral AI●ProprietaryText generation / LLMCohere logoCohere logoCommand R+closedCohere●ProprietaryText generation / LLMOpenAI logoOpenAI logoDALL·E 3closedOpenAI●ProprietaryText to imageOpenAI logoOpenAI logoSoraclosedOpenAI●ProprietaryText to videoOpenAI logoOpenAI logoWhisper (API)closedOpenAI●ProprietarySpeech recognitionMidjourney v6closedMidjourney●ProprietaryText to imageFLUX.1-devopenblack-forest-labs●otherText to image↓ 620K★ 13.6KDeepSeek logoDeepSeek logoDeepSeek-R1opendeepseek-ai●MITText generation / LLM↓ 8.7M★ 13.5KQwen logoQwen3.8-27BopenQwen●Apache 2.0Multimodal (vision-language)↓ 91.9K★ 9.9KKimi-K3openmoonshotai●otherMultimodal (vision-language)↓ 559.9K★ 9.5Kstable-diffusion-xl-base-1.0openstabilityai●OpenRAIL++Text to image↓ 1.4M★ 7.9Kstable-diffusion-v1-4openCompVis●CreativeML OpenRAIL-MText to image↓ 453.5K★ 7KMeta logoMeta-Llama-3-8Bopenmeta-llama●Llama 3 Community LicenseText generation / LLM↓ 1.3M★ 6.6KKokoro-82Mopenhexgrad●Apache 2.0Text to speech↓ 11.3M★ 6.5KMeta logoLlama-3.1-8B-Instructopenmeta-llama●Llama 3.1 Community LicenseText generation / LLM↓ 8.5M★ 6.3KOpenAI logoOpenAI logowhisper-large-v3openopenai●Apache 2.0Speech recognition↓ 6M★ 5.9KFLUX.1-schnellopenblack-forest-labs●Apache 2.0Text to image↓ 244.1K★ 5.3KDeepSeek logoDeepSeek logoDeepSeek-V4-Proopendeepseek-ai●MITText generation / LLM↓ 1.4M★ 5.2Kbloomopenbigscience●BigScience BLOOM RAIL 1.0Text generation / LLM↓ 5.5K★ 5Kstable-diffusion-3-mediumopenstabilityai●otherText to image↓ 3.6K★ 5KZ-Image-TurboopenTongyi-MAI●Apache 2.0Text to image↓ 994.3K★ 5KOpenAI logoOpenAI logogpt-oss-120bopenopenai●Apache 2.0Text generation / LLM↓ 4.4M★ 5KMeta logoLlama-2-7b-chat-hfopenmeta-llama●Llama 2 Community LicenseText generation / LLM↓ 287.2K★ 4.8KOpenAI logoOpenAI logogpt-oss-20bopenopenai●Apache 2.0Text generation / LLM↓ 7.3M★ 4.8KMeta logoMeta-Llama-3-8B-Instructopenmeta-llama●Llama 3 Community LicenseText generation / LLM↓ 1.4M★ 4.7KMeta logoLlama-2-7bopenmeta-llama●Llama 2 Community LicenseText generation / LLM↓ 126★ 4.5KQwen logoQwen3.8-Flash-NextopenQwen●otherMultimodal (vision-language)↓ 52.3K★ 4.3KMistral AI logoMistral-7B-v0.1openmistralai●Apache 2.0Text generation / LLM↓ 748.8K★ 4.1KDeepSeek logoDeepSeek logoDeepSeek-V3opendeepseek-ai●Not specifiedText generation / LLM↓ 1M★ 4.1KOrangeMixsopenWarriorMama777●CreativeML OpenRAIL-MText to image↓ 858★ 3.9KGLM-5.2openzai-org●MITText generation / LLM↓ 441.4K★ 3.8KXTTS-v2opencoqui●otherText to speech↓ 10M★ 3.7Kstable-diffusion-3.5-largeopenstabilityai●otherText to image↓ 34.9K★ 3.6KEdge0-35B-A3B-previewopenEdge0●Apache 2.0Text generation / LLM↓ 68.4K★ 3.5Kphi-2openmicrosoft●MITText generation / LLM↓ 851.4K★ 3.5KGoogle logogemma-7bopengoogle●Gemma Terms of UseText generation / LLM↓ 28.7K★ 3.4KOpenAI logoOpenAI logogpt2openopenai-community●MITText generation / LLM↓ 13.7M★ 3.3KJEV-27B-VLopenautotrust●Apache 2.0Multimodal (vision-language)↓ 1.5M★ 3.3KDeepSeek logoDeepSeek logoDeepSeek-OCRopendeepseek-ai●MITMultimodal (vision-language)↓ 2.6M★ 3.3Kopenjourneyopenprompthero●CreativeML OpenRAIL-MText to image↓ 5.5K★ 3.2KMistral AI logoMistral-7B-Instruct-v0.2openmistralai●Apache 2.0Text generation / LLM↓ 1.1M★ 3.2KGoogle logogemma-4-31B-itopengoogle●Apache 2.0Multimodal (vision-language)↓ 12.2M★ 3.2KOpenAI logoOpenAI logowhisper-large-v3-turboopenopenai●MITSpeech recognition↓ 7.9M★ 3.2KDeepSeek logoDeepSeek logoDeepSeek-V3-0324opendeepseek-ai●MITText generation / LLM↓ 749.8K★ 3.1Kstarcoderopenbigcode●BigCode OpenRAIL-MText generation / LLM↓ 21.7K★ 3KQwen logoQwQ-32BopenQwen●Apache 2.0Text generation / LLM↓ 382.3K★ 2.9KQwen3.5-27B-Claude-4.6-Opus-Reasoning-DistilledopenJackrong●Apache 2.0Multimodal (vision-language)↓ 137.1K★ 2.9KDia-1.6Bopennari-labs●Apache 2.0Text to speech↓ 3.4K★ 2.9KMeta logoLlama-3.3-70B-Instructopenmeta-llama●Llama 3.3 Community LicenseText generation / LLM↓ 762.1K★ 2.9Kstable-diffusion-v-1-4-originalopenCompVis●CreativeML OpenRAIL-MText to image↓ 2★ 2.9KDeepSeek logoDeepSeek logoDeepSeek-V4-Flash-0731opendeepseek-ai●MITText generation / LLM↓ 785.8K★ 2.9KKimi-K2.5openmoonshotai●otherMultimodal (vision-language)↓ 1.2M★ 2.8KLocateAnything-3Bopennvidia●otherMultimodal (vision-language)↓ 1.5M★ 2.7KGoogle logobert-base-uncasedopengoogle-bert●Apache 2.0Masked language model↓ 72.6M★ 2.7Kgemma-4-12B-coder-fable5-composer2.5-v1-GGUFopenyuxinlu1●Apache 2.0Text generation / LLM↓ 726.6K★ 2.7Kspeaker-diarization-3.1openpyannote●MITSpeech recognition↓ 8.4M★ 2.7KQwen3.6-35B-A3B-Uncensored-HauhauCS-AggressiveopenHauhauCS●Apache 2.0Multimodal (vision-language)↓ 2.6M★ 2.7Ksdxl-turboopenstabilityai●otherText to image↓ 778.3K★ 2.6KQwen logoQwen-ImageopenQwen●Apache 2.0Text to image↓ 188.6K★ 2.5KNeoHorse-1-4BopenTokenRhythm●Apache 2.0Text generation / LLM↓ 24.7K★ 2.5Kwaifu-diffusionopenhakurei●CreativeML OpenRAIL-MText to image↓ 1.5K★ 2.5KMeta logoLlama-3.2-1Bopenmeta-llama●Llama 3.2 Community LicenseText generation / LLM↓ 1.8M★ 2.5KDeepSeek logoDeepSeek logoDeepSeek-R1-0528opendeepseek-ai●MITText generation / LLM↓ 833.4K★ 2.5Kfalcon-40bopentiiuae●Apache 2.0Text generation / LLM↓ 29.9K★ 2.4KxAI logogrok-1openxai-org●Apache 2.0Text generation / LLM↓ 198★ 2.4KVibeVoice-1.5Bopenmicrosoft●MITText to speech↓ 72.1K★ 2.4Kcsm-1bopensesame●Apache 2.0Text to speech↓ 260.3K★ 2.4KQwen logoQwen-Image-2.1openQwen●otherText to image↓ 48.4K★ 2.4KQwen logoQwen3.6-35B-A3BopenQwen●Apache 2.0Multimodal (vision-language)↓ 6.7M★ 2.4KKimi-K2-Instructopenmoonshotai●otherText generation / LLM↓ 295.1K★ 2.4KMeta logoLlama-2-7b-hfopenmeta-llama●Llama 2 Community LicenseText generation / LLM↓ 686.4K★ 2.3KMeta logoLlama-3.2-3B-Instructopenmeta-llama●Llama 3.2 Community LicenseText generation / LLM↓ 2.2M★ 2.3KMeta logoLlama-3.1-8Bopenmeta-llama●Llama 3.1 Community LicenseText generation / LLM↓ 1.6M★ 2.3KQwen-Image-Edit-Rapid-AIOopenPhr00t●Apache 2.0Text to image★ 2.3Kphi-4openmicrosoft●MITText generation / LLM↓ 873.8K★ 2.3KQwen logoQwen2.5-7B-InstructopenQwen●Apache 2.0Text generation / LLM↓ 9.7M★ 2.2KHunyuanVideoopentencent●otherText to video↓ 823★ 2.2KMeta logoLlama-2-70b-chat-hfopenmeta-llama●Llama 2 Community LicenseText generation / LLM↓ 7.7K★ 2.2KSDXL-LightningopenByteDance●OpenRAIL++Text to image↓ 72.7K★ 2.2KGLM-5.3openzai-org●otherText generation / LLM↓ 1.6M★ 2.1KTernary-Bonsai-2-27B-ggufopenprism-ml●Apache 2.0Text generation / LLM↓ 3.2M★ 2.1KGLM-5openzai-org●MITText generation / LLM↓ 53.8K★ 2.1KGLM-5.3-Flashopenzai-org●MITMultimodal (vision-language)↓ 727.6K★ 2.1KQwen logoQwen2.5-Coder-32B-InstructopenQwen●Apache 2.0Text generation / LLM↓ 1.4M★ 2.1KLlama-3.1-Nemotron-70B-Instruct-HFopennvidia●Llama 3.1 Community LicenseText generation / LLM↓ 41.3K★ 2.1KGLM-4.7openzai-org●MITText generation / LLM↓ 59.8K★ 2KQwythos-9B-Claude-Mythos-5-1M-GGUFopenempero-ai●Apache 2.0Multimodal (vision-language)↓ 2M★ 2KDeepSeek logoDeepSeek logoDeepSeek-V4.1-Flashopendeepseek-ai●MITMultimodal (vision-language)↓ 140.6K★ 2KGoogle logogemma-3-27b-itopengoogle●Gemma Terms of UseMultimodal (vision-language)↓ 856.1K★ 2KQwen logoQwen3.6-27BopenQwen●Apache 2.0Multimodal (vision-language)↓ 4.9M★ 2KQwen-Image-2.1-Uncensored-GGUFopenabenzerps●otherText to image↓ 876.7K★ 2KUnlimited-OCRopenbaidu●MITMultimodal (vision-language)↓ 1.4M★ 1.9KGLM-OCRopenzai-org●MITMultimodal (vision-language)↓ 3.1M★ 1.9KclefopenCloudflare●Apache 2.0Multimodal (vision-language)↓ 12.1K★ 1.9KSulphur-2-baseopenSulphurAI●Not specifiedText to video↓ 542.5K★ 1.9KIP-Adapter-FaceIDopenh94●Not specifiedText to image↓ 175.5K★ 1.9Kzephyr-7b-betaopenHuggingFaceH4●MITText generation / LLM↓ 184.5K★ 1.8KMistral AI logoMistral-7B-Instruct-v0.1openmistralai●Apache 2.0Text generation / LLM↓ 307.1K★ 1.8KGLM-5.1openzai-org●MITText generation / LLM↓ 95.6K★ 1.8KFlorence-2-largeopenmicrosoft●MITMultimodal (vision-language)↓ 813.2K★ 1.8KDeepSeek logoDeepSeek logoDeepSeek-V4-Flashopendeepseek-ai●MITText generation / LLM↓ 3.2M★ 1.8KCohere logoCohere logoc4ai-command-r-plusopenCohereLabs●CC BY-NC 4.0Text generation / LLM↓ 2.2K★ 1.8KOpenAI logoOpenAI logowhisper-large-v2openopenai●Apache 2.0Speech recognition↓ 114.1K★ 1.8Kcontrolnet-union-sdxl-1.0openxinsir●Apache 2.0Text to image↓ 139.1K★ 1.8KQwen3.8-27B-GSQ-RCO-GGUFopenISTA-DASLab●Apache 2.0Multimodal (vision-language)↓ 1.6M★ 1.7Kdreamlike-photoreal-2.0opendreamlike-art●otherText to image↓ 6K★ 1.7KOmniParseropenmicrosoft●MITMultimodal (vision-language)↓ 338★ 1.7KQwen logoQwen3-TTS-12Hz-1.7B-CustomVoiceopenQwen●Apache 2.0Text to speech↓ 2.3M★ 1.7KQwen logoQwen3.5-9BopenQwen●Apache 2.0Multimodal (vision-language)↓ 8.8M★ 1.7KGemma-4-31B-JANG_4M-CRACKopendealignai●Gemma Terms of UseMultimodal (vision-language)↓ 34.7K★ 1.7KchatterboxopenResembleAI●MITText to speech↓ 2.7M★ 1.7KChatTTSopen2Noise●CC BY-NC 4.0Text to audio↓ 2.6K★ 1.7KPaddleOCR-VLopenPaddlePaddle●Apache 2.0Multimodal (vision-language)↓ 29.3K★ 1.6KQwen logoQwen2.5-VL-7B-InstructopenQwen●Apache 2.0Multimodal (vision-language)↓ 10.2M★ 1.6KMeta logoLlama-3.2-11B-Vision-Instructopenmeta-llama●Llama 3.2 Community LicenseMultimodal (vision-language)↓ 81.8K★ 1.6KSmolDocling-256M-previewopendocling-project●CDLA-Permissive 2.0Multimodal (vision-language)↓ 28.3K★ 1.6KPhi-4-multimodal-instructopenmicrosoft●MITSpeech recognition↓ 516.8K★ 1.6KQwen3.8-27B-Uncensored-HauhauCS-Aggressive-MTP-GGUFopenHauhauCS●Apache 2.0Multimodal (vision-language)↓ 2.1M★ 1.6KNanonets-OCR-sopennanonets●Not specifiedMultimodal (vision-language)↓ 10.1K★ 1.6KQwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUFopenDavidAU●Apache 2.0Multimodal (vision-language)↓ 2M★ 1.6KZDTaichu5.0-9BopenTaichuAI●Not specifiedMultimodal (vision-language)↓ 11.1K★ 1.6KMeta logoMuse-Glimmer-30Bopenmeta-models●Apache 2.0Multimodal (vision-language)↓ 246.5K★ 1.6KCounterfeit-V2.5opengsdf●CreativeML OpenRAIL-MText to image↓ 8.7K★ 1.6KInklingopenthinkingmachines●Apache 2.0Multimodal (vision-language)↓ 31.6K★ 1.6KGOT-OCR2_0openstepfun-ai●Apache 2.0Multimodal (vision-language)↓ 199.4K★ 1.5Kbarkopensuno●MITText to speech↓ 25.2K★ 1.5KWan2.1-T2V-14BopenWan-AI●Apache 2.0Text to video↓ 72K★ 1.5KQwen logoQwen3.5-397B-A17BopenQwen●Apache 2.0Multimodal (vision-language)↓ 435.6K★ 1.5Kstable-audio-open-1.0openstabilityai●otherText to audio↓ 21K★ 1.5Kparakeet-tdt-0.6b-v2opennvidia●CC BY 4.0Speech recognition↓ 406.9K★ 1.5KKimi-K2.6openmoonshotai●otherMultimodal (vision-language)↓ 1.6M★ 1.5Kwhisper.cppopenggerganov●MITSpeech recognition★ 1.5KGoogle logogemma-3n-E4B-it-litert-previewopengoogle●Gemma Terms of UseMultimodal (vision-language)★ 1.5Kblip-image-captioning-largeopenSalesforce●BSD 3-ClauseImage to text↓ 807.4K★ 1.5KVoxCPM2openopenbmb●Apache 2.0Text to speech↓ 920.4K★ 1.5KQwen logoQwen3.5-35B-A3BopenQwen●Apache 2.0Multimodal (vision-language)↓ 2.4M★ 1.5KGoogle logobert-base-chineseopengoogle-bert●Apache 2.0Masked language model↓ 801.8K★ 1.4KQwen3.8-27B-Uncensored-MLXopenorcarouter●Apache 2.0Multimodal (vision-language)↓ 169.2K★ 1.4KQwen3.5-35B-A3B-Uncensored-HauhauCS-AggressiveopenHauhauCS●Apache 2.0Multimodal (vision-language)↓ 136.2K★ 1.4KQwen3.8-27B-Uncensored-FP8openorcarouter●Apache 2.0Multimodal (vision-language)↓ 369.1K★ 1.4Kmoondream2openvikhyatk●Apache 2.0Multimodal (vision-language)↓ 1.9M★ 1.4Kstable-diffusion-xl-base-0.9openstabilityai●otherText to image↓ 43★ 1.4Ksd-vae-ft-mse-originalopenstabilityai●MITText to image↓ 1★ 1.4KMiniCPM-Llama3-V-2_5openopenbmb●Not specifiedMultimodal (vision-language)↓ 15K★ 1.4KGoogle logogemma-3-4b-itopengoogle●Gemma Terms of UseMultimodal (vision-language)↓ 2.3M★ 1.4KFLUX.1-dev-ggufopencity96●otherText to image↓ 131.7K★ 1.4KIP-Adapteropenh94●Apache 2.0Text to image★ 1.4KChromaopenlodestones●Apache 2.0Text to image★ 1.4KQwen3.6-35B-A3B-GGUFopenunsloth●Apache 2.0Multimodal (vision-language)↓ 854.4K★ 1.3KHyper-SDopenByteDance●Not specifiedText to image↓ 51.7K★ 1.3Kmochi-1-previewopengenmo●Apache 2.0Text to video↓ 4.4K★ 1.3Kstable-cascadeopenstabilityai●otherText to image↓ 7.9K★ 1.3KMiniMax-M3openMiniMaxAI●otherMultimodal (vision-language)↓ 267.1K★ 1.3KMeta logoLlama-4-Scout-17B-16E-Instructopenmeta-llama●otherMultimodal (vision-language)↓ 630.7K★ 1.3Kdots.ocropendots-studio●MITMultimodal (vision-language)↓ 450K★ 1.3Kdots.ocropenrednote-hilab●MITMultimodal (vision-language)↓ 411.1K★ 1.3Kspeaker-diarizationopenpyannote●MITSpeech recognition↓ 523.9K★ 1.3KQwen logoQwen2-VL-7B-InstructopenQwen●Apache 2.0Multimodal (vision-language)↓ 1.7M★ 1.3KKimi-K2.7-Codeopenmoonshotai●otherMultimodal (vision-language)↓ 749.4K★ 1.3KGoogle logoembeddinggemma-2opengoogle●Apache 2.0Embeddings↓ 29.2K★ 1.3KGoogle logogemma-4-26B-A4B-itopengoogle●Apache 2.0Multimodal (vision-language)↓ 14.3M★ 1.3Kopenjourney-v4openprompthero●CreativeML OpenRAIL-MText to image↓ 1.3K★ 1.3KQwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUFopenDavidAU●Apache 2.0Multimodal (vision-language)↓ 1.2M★ 1.2KVibeVoice-Realtime-0.5Bopenmicrosoft●MITText to speech↓ 654.3K★ 1.2Kflux-RealismLoraopenXLabs-AI●otherText to image↓ 12.3K★ 1.2Kmultilingual-e5-largeopenintfloat●MITEmbeddings↓ 12.9M★ 1.2Kgranite-docling-258Mopenibm-granite●Apache 2.0Multimodal (vision-language)↓ 69.4K★ 1.2KVibeVoice-ASRopenmicrosoft●MITSpeech recognition↓ 706.9K★ 1.2KQianfan-OCRopenbaidu●Apache 2.0Multimodal (vision-language)↓ 237.9K★ 1.2KF5-TTSopenSWivid●CC BY-NC 4.0Text to speech↓ 755.2K★ 1.2Kstable-diffusion-v1-5openstable-diffusion-v1-5●CreativeML OpenRAIL-MText to image↓ 1.7M★ 1.2KZ-ImageopenTongyi-MAI●Apache 2.0Text to image↓ 21.6K★ 1.2KOmniVoiceopenk2-fsa●Not specifiedText to speech↓ 968.3K★ 1.2Kjina-embeddings-v3openjinaai●CC BY-NC 4.0Embeddings↓ 3M★ 1.1KMiniCPM-V-4.6openopenbmb●Apache 2.0Multimodal (vision-language)↓ 975.1K★ 1.1Kwaifu-diffusion-v1-4openhakurei●CreativeML OpenRAIL-MText to image★ 1.1KGoogle logodiffusiongemma-26B-A4B-itopengoogle●Apache 2.0Multimodal (vision-language)↓ 2M★ 1.1KQwen logoQwen3-Embedding-0.6BopenQwen●Apache 2.0Embeddings↓ 11M★ 1.1KZonos-v0.1-hybridopenZyphra●Apache 2.0Text to speech↓ 1.7K★ 1.1KHunyuanImage-3.0opentencent●otherText to image↓ 5.5K★ 1.1KGLM-Imageopenzai-org●MITText to image↓ 36.8K★ 1.1Ks2-proopenfishaudio●otherText to speech↓ 418.9K★ 1.1KModernBERT-baseopenanswerdotai●Apache 2.0Masked language model↓ 9.2M★ 1.1KKrea-2-Turboopenkrea●otherText to image↓ 77.5K★ 1.1KCohere logoCohere logocohere-transcribe-03-2026openCohereLabs●Apache 2.0Speech recognition↓ 816.7K★ 1Kdreamlike-diffusion-1.0opendreamlike-art●otherText to image↓ 4.6K★ 1KHunyuanVideo-1.5opentencent●otherText to video↓ 3.8K★ 1KDreamShaperopenLykon●otherText to image↓ 243.2K★ 1Kstable-diffusion-3.5-mediumopenstabilityai●otherText to image↓ 614.1K★ 1KKrea-2-Rawopenkrea●otherText to image↓ 83.1K★ 1KHiDream-I1-FullopenHiDream-ai●MITText to image↓ 11.3K★ 997Meta logoseamless-m4t-v2-largeopenfacebook●CC BY-NC 4.0Speech recognition↓ 108.9K★ 993AnimateDiff-LightningopenByteDance●CreativeML OpenRAIL-MText to video↓ 11.8K★ 993parakeet-tdt-0.6b-v3opennvidia●CC BY 4.0Speech recognition↓ 100.4K★ 991Inkpunk-DiffusionopenEnvvi●CreativeML OpenRAIL-MText to image↓ 257★ 989basil_mixopennuigurumi●otherText to image↓ 664★ 980SRPOopentencent●otherText to image↓ 487★ 976vit-gpt2-image-captioningopennlpconnect●Apache 2.0Image to text↓ 70.4K★ 931Qwen logoQwen3-ASR-1.7BopenQwen●Apache 2.0Speech recognition↓ 1.5M★ 924Mistral AI logoVoxtral-Mini-4B-Realtime-2602openmistralai●Apache 2.0Speech recognition↓ 2M★ 911distilbert-base-uncasedopendistilbert●Apache 2.0Masked language model↓ 9.4M★ 911maya1openmaya-research●Apache 2.0Text to speech↓ 3.2K★ 888supertonic-3openSupertone●OpenRAILText to speech↓ 64.3K★ 878neutts-airopenneuphonic●Apache 2.0Text to speech↓ 10.5K★ 877Mistral AI logoVoxtral-4B-TTS-2603openmistralai●CC BY-NC 4.0Text to speech↓ 46.2K★ 877blip-image-captioning-baseopenSalesforce●BSD 3-ClauseImage to text↓ 1.7M★ 865Meta logoxlm-roberta-baseopenFacebookAI●MITMasked language model↓ 22.8M★ 864pyramid-flow-sd3openrain1011●otherText to video★ 838speecht5_ttsopenmicrosoft●MITText to speech↓ 71.7K★ 836Audio8-ASR-InfiniteopenEdge0●Apache 2.0Speech recognition↓ 7.9K★ 835nemotron-3.5-asr-streaming-0.6bopennvidia●otherSpeech recognition↓ 276K★ 820mxbai-embed-large-v1openmixedbread-ai●Apache 2.0Embeddings↓ 5M★ 814VoxCPM-0.5Bopenopenbmb●Apache 2.0Text to speech↓ 4.8K★ 808Ace-Step1.5openACE-Step●MITText to audio↓ 48.4K★ 791metavoice-1B-v0.1openmetavoiceio●Apache 2.0Text to speech↓ 166★ 789MiniMax-Music3openMiniMaxAI●Not specifiedText to audio↓ 5.1K★ 776fish-speech-1.5openfishaudio●CC BY-NC-SA 4.0Text to speech↓ 4.2K★ 756IndexTTS-2openIndexTeam●Not specifiedText to speech↓ 15.4K★ 747Spark-TTS-0.5BopenSparkAudio●CC BY-NC-SA 4.0Text to speech↓ 788★ 742Qwen logoQwen3-Embedding-8BopenQwen●Apache 2.0Embeddings↓ 2.9M★ 741ACE-Step-v1-3.5BopenACE-Step●Apache 2.0Text to audio★ 739jina-embeddings-v2-base-enopenjinaai●Apache 2.0Embeddings↓ 417.7K★ 735speaker-diarization-community-1openpyannote●CC BY 4.0Speech recognition↓ 4.3M★ 729orpheus-3b-0.1-ftopencanopylabs●Apache 2.0Text to speech↓ 24.4K★ 705bge-large-en-v1.5openBAAI●MITEmbeddings↓ 14.7M★ 698Wan2.2-TI2V-5BopenWan-AI●Apache 2.0Text to video↓ 14.6K★ 692higgs-tts-2-3b-baseopenbosonai●otherText to speech↓ 124.6K★ 689CogVideoX-5bopenzai-org●otherText to video↓ 15.2K★ 677s1-miniopenfishaudio●CC BY-NC-SA 4.0Text to speech↓ 2.4K★ 670chatterbox-turboopenResembleAI●MITText to speech★ 666text-to-video-ms-1.7bopenali-vilab●CC BY-NC 4.0Text to video↓ 111.2K★ 666riffusion-model-v1openriffusion●CreativeML OpenRAIL-MText to audio↓ 1.1K★ 650bge-large-zh-v1.5openBAAI●MITEmbeddings↓ 1.5M★ 642multilingual-e5-large-instructopenintfloat●MITEmbeddings↓ 1.9M★ 629higgs-tts-3-4bopenbosonai●otherText to speech↓ 199.1K★ 625Meta logoroberta-baseopenFacebookAI●MITMasked language model↓ 9.1M★ 625Wan2.2-Lightningopenlightx2v●Apache 2.0Text to video↓ 353★ 623faster-whisper-large-v3openSystran●MITSpeech recognition↓ 1.2M★ 616Wan14BT2VFusioniXopenvrgamedevgirl84●Apache 2.0Text to video↓ 15.6K★ 614Google logobert-base-multilingual-casedopengoogle-bert●Apache 2.0Masked language model↓ 2.8M★ 598nemotron-speech-streaming-en-0.6bopennvidia●otherSpeech recognition↓ 103.7K★ 591Fun-CosyVoice3-0.5B-2512openFunAudioLLM●Apache 2.0Text to speech↓ 25.7K★ 581OpenAI logoOpenAI logowhisper-smallopenopenai●Apache 2.0Speech recognition↓ 3.3M★ 574e5-mistral-7b-instructopenintfloat●MITEmbeddings↓ 448.7K★ 568OpenAI logoOpenAI logowhisper-largeopenopenai●Apache 2.0Speech recognition↓ 36K★ 549LongCat-Videoopenmeituan-longcat●MITText to video↓ 2K★ 534Meta logomusicgen-largeopenfacebook●CC BY-NC 4.0Text to audio↓ 23.6K★ 533Llasa-3BopenHKUSTAudio●CC BY-NC 4.0Text to speech↓ 612★ 528Meta logoxlm-roberta-largeopenFacebookAI●MITMasked language model↓ 7.6M★ 521Wan2.2-T2V-A14BopenWan-AI●Apache 2.0Text to video↓ 3.6K★ 519distil-large-v2opendistil-whisper●MITSpeech recognition↓ 5.1K★ 516Meta logoseamless-m4t-largeopenfacebook●CC BY-NC 4.0Speech recognition★ 513NV-Embed-v2opennvidia●CC BY-NC 4.0Embeddings↓ 17.9K★ 513bge-small-en-v1.5openBAAI●MITEmbeddings↓ 66.4M★ 508trocr-base-handwrittenopenmicrosoft●MITImage to text↓ 142.1K★ 499OpenVoiceV2openmyshell-ai●MITText to speech★ 496Meta logomusicgen-smallopenfacebook●CC BY-NC 4.0Text to audio↓ 242.9K★ 496zeroscope_v2_576wopencerspense●CC BY-NC 4.0Text to video↓ 13.1K★ 493MiniMax-H3-Turbo-Loraopenlarryvrh●Apache 2.0Text to video★ 493OpenVoiceopenmyshell-ai●MITText to speech★ 488supertonicopenSupertone●OpenRAILText to speech↓ 531★ 482Wan2.1-T2V-1.3BopenWan-AI●Apache 2.0Text to video↓ 48.7K★ 482MARS5-TTSopenCAMB-AI●AGPL 3.0Text to speech↓ 56★ 480modelscope-damo-text-to-video-synthesisopenali-vilab●CC BY-NC 4.0Text to video↓ 152★ 479stepvideo-t2vopenstepfun-ai●MITText to video↓ 35★ 479NuMarkdown-8B-Thinkingopennumind●MITImage to text↓ 32.2K★ 477wav2vec2-large-xlsr-53-englishopenjonatasgrosman●Apache 2.0Speech recognition↓ 59K★ 476ModernBERT-largeopenanswerdotai●Apache 2.0Masked language model↓ 3.5M★ 474bge-reranker-largeopenBAAI●MITEmbeddings↓ 2.1M★ 465fish-speech-1.4openfishaudio●CC BY-NC-SA 4.0Text to speech↓ 678★ 458canary-1bopennvidia●CC BY-NC 4.0Speech recognition↓ 2.3K★ 457bge-base-en-v1.5openBAAI●MITEmbeddings↓ 8.7M★ 450Breeze-TTS-2openBreezeBlue●otherText to speech↓ 6K★ 449canary-qwen-2.5bopennvidia●CC BY 4.0Speech recognition↓ 78.8K★ 446mini-omniopengpt-omni●MITText to speech↓ 1★ 443OpenAI logoOpenAI logowhisper-tinyopenopenai●Apache 2.0Speech recognition↓ 1.8M★ 434Zonos-v0.1-transformeropenZyphra●Apache 2.0Text to speech↓ 10.5K★ 434SenseVoiceSmallopenFunAudioLLM●otherSpeech recognition↓ 18.1K★ 433Bio_ClinicalBERTopenemilyalsentzer●MITMasked language model↓ 4.3M★ 433deberta-v3-baseopenmicrosoft●MITMasked language model↓ 2.7M★ 430Confucius4-R2T2opennetease-youdao●otherSpeech recognition↓ 7.2K★ 427PinkCherry-NSFW_MiniMax-H3openSexGod1979●Apache 2.0Text to video↓ 734★ 425MOSS-TTSopenOpenMOSS-Team●Apache 2.0Text to speech↓ 8.8K★ 423Inflect-Micro-v2openowensong●Apache 2.0Text to speech↓ 2.3K★ 422chinese-roberta-wwm-extopenhfl●Apache 2.0Masked language model↓ 120K★ 420MegaTTS3openByteDance●Apache 2.0Text to speech↓ 155★ 419GPT-SoVITSopenlj1995●MITText to speech★ 416canary-1b-v2opennvidia●CC BY 4.0Speech recognition↓ 91.4K★ 402Meta logowav2vec2-base-960hopenfacebook●Apache 2.0Speech recognition↓ 1.6M★ 398bce-embedding-base_v1openmaidalun1020●Apache 2.0Embeddings↓ 12.3K★ 394GLM-ASR-Nano-2512openzai-org●MITSpeech recognition↓ 147.7K★ 383ClinicalBERTopenmedicalai●Not specifiedMasked language model↓ 20.1K★ 377distil-large-v3opendistil-whisper●MITSpeech recognition↓ 1M★ 376CogVideoX-2bopenzai-org●Apache 2.0Text to video↓ 19.7K★ 366Google logobert-base-casedopengoogle-bert●Apache 2.0Masked language model↓ 3.2M★ 364AnimateLCMopenwangfuyun●Not specifiedText to video↓ 13.7K★ 347Google logomedasropengoogle●otherSpeech recognition↓ 196.5K★ 345bge-large-zhopenBAAI●MITEmbeddings↓ 20K★ 345jina-clip-v2openjinaai●CC BY-NC 4.0Embeddings↓ 459.4K★ 341CrisperWhisperopennyrahealth●CC BY-NC 4.0Speech recognition↓ 48.2K★ 336CrisperWhisperopennyralabs●CC BY-NC 4.0Speech recognition↓ 40.9K★ 336BiomedNLP-BiomedBERT-base-uncased-abstract-fulltextopenmicrosoft●MITMasked language model↓ 286.8K★ 329YuE2-3Bopenm-a-p●CC BY-NC 4.0Text to audio↓ 2.3K★ 327Hotshot-XLopenhotshotco●OpenRAIL++Text to video↓ 3.3K★ 318whistleopenCactus-Compute●Apache 2.0Speech recognition↓ 12.8K★ 316Qwen logoQwen3-ASR-0.6BopenQwen●Apache 2.0Speech recognition↓ 1.2M★ 313legal-bert-base-uncasedopennlpaueb●CC BY-SA 4.0Masked language model↓ 130.6K★ 313mimiopenkyutai●CC BY 4.0Embeddings↓ 499.4K★ 311Meta logoroberta-largeopenFacebookAI●MITMasked language model↓ 13.4M★ 308Geneformeropenctheodoris●Apache 2.0Masked language model↓ 4.8K★ 303SFR-Embedding-MistralopenSalesforce●CC BY-NC 4.0Embeddings↓ 22K★ 299Qwen logoQwen3-Embedding-4BopenQwen●Apache 2.0Embeddings↓ 2.8M★ 293codebert-baseopenmicrosoft●Not specifiedEmbeddings↓ 332.9K★ 288OpenAI logoOpenAI logowhisper-mediumopenopenai●Apache 2.0Speech recognition↓ 381.7K★ 287krea-realtime-videoopenkrea●Apache 2.0Text to video↓ 323★ 286cde-small-v1openjxm●Not specifiedEmbeddings↓ 149★ 284deberta-v3-largeopenmicrosoft●MITMasked language model↓ 2M★ 283Phonon-2openFermionResearch●CC BY 4.0Speech recognition↓ 4.1K★ 281NuExtract3opennumind●Apache 2.0Image to text↓ 1.1M★ 280FastVideo-FastH3-4-step-Preview-v1-VSA-DataFreeopenFastVideo●otherText to video↓ 22.9K★ 279OpenAI logoOpenAI logowhisper-baseopenopenai●Apache 2.0Speech recognition↓ 6.5M★ 275canary-1b-flashopennvidia●CC BY 4.0Speech recognition↓ 4.4K★ 275harrier-oss-v1-0.6bopenmicrosoft●MITEmbeddings↓ 348.4K★ 268LTX-2.3-uncensored-v1.4-FP8openChrisColeTech●unknownText to video↓ 62.8K★ 268Wan2.2-T2V-A14B-GGUFopenQuantStack●Apache 2.0Text to video↓ 98.1K★ 265Allegroopenrhymes-ai●Apache 2.0Text to video↓ 143★ 264stable-audio-open-smallopenstabilityai●otherText to audio↓ 2.2K★ 264LTX-Best-Face-IDopenAlissonerdx●otherText to video★ 259HeartMuLa-oss-3BopenHeartMuLa●Apache 2.0Text to audio↓ 836★ 257jina-clip-v1openjinaai●Apache 2.0Embeddings↓ 64.5K★ 256Meta logomusicgen-melodyopenfacebook●CC BY-NC 4.0Text to audio↓ 6.6K★ 254donut-baseopennaver-clova-ix●MITImage to text↓ 138.2K★ 254LightOnOCR-1B-1025openlightonai●Apache 2.0Image to text↓ 173.3K★ 254MiniCPM-Embeddingopenopenbmb●Not specifiedEmbeddings↓ 2K★ 253granite-4.0-1b-speechopenibm-granite●Apache 2.0Speech recognition↓ 112.3K★ 249jina-embeddings-v2-base-zhopenjinaai●Apache 2.0Embeddings↓ 11.9K★ 246Wan2.1_14B_VACE-GGUFopenQuantStack●Apache 2.0Text to video↓ 9.7K★ 244distilbert-base-multilingual-casedopendistilbert●Apache 2.0Masked language model↓ 751.9K★ 244VibeVoice-ASR-Streaming-7Bopenmicrosoft●MITSpeech recognition↓ 6.1K★ 243voice-activity-detectionopenpyannote●MITSpeech recognition↓ 3.7M★ 239UAE-Large-V1openWhereIsAI●MITEmbeddings↓ 1.2M★ 237Cosmos-1.0-Diffusion-7B-Text2Worldopennvidia●otherText to video↓ 1.4K★ 234bert-base-portuguese-casedopenneuralmind●MITMasked language model↓ 431.4K★ 232Google logomagenta-realtime-2opengoogle●CC BY 4.0Text to audio↓ 13.2K★ 231chinese-roberta-wwm-ext-largeopenhfl●Apache 2.0Masked language model↓ 25K★ 230mdeberta-v3-baseopenmicrosoft●MITMasked language model↓ 1.8M★ 229nemotron-ocr-v2opennvidia●otherImage to text↓ 13.3K★ 228bge-large-enopenBAAI●MITEmbeddings↓ 87.5K★ 227llava-llama-3-8b-v1_1-ggufopenxtuner●Not specifiedImage to text↓ 3K★ 225Meta logow2v-bert-2.0openfacebook●MITEmbeddings↓ 3.1M★ 223Fun-ASR-Nano-2512openFunAudioLLM●Apache 2.0Speech recognition↓ 3.2K★ 223speaker-diarization-3.0openpyannote●MITSpeech recognition↓ 223K★ 221pplx-embed-v1-0.6bopenperplexity-ai●MITEmbeddings↓ 748K★ 221mmBERT-baseopenjhu-clsp●MITMasked language model↓ 479.6K★ 221stable-audio-3-mediumopenstabilityai●otherText to audio↓ 49.9K★ 218trocr-base-printedopenmicrosoft●Not specifiedImage to text↓ 290.8K★ 213Minimax-H3-fl2va-ref2va-hybrid-modelsopensmhfacct●otherText to video★ 213MiniMax-H3-Turbo-Lora-ComfyUIopendrbaph●Apache 2.0Text to video★ 212Qwen logoMiniMax-H3-Acc-LoRAsopenalibaba-pai●otherText to video↓ 59.3K★ 211embeddinggemma-2-GGUFopenunsloth●Apache 2.0Embeddings↓ 41.6K★ 208OCR-Donut-CORDopenjinhybr●MITImage to text↓ 14★ 207Meta logobart-baseopenfacebook●Apache 2.0Embeddings↓ 459.6K★ 206Wan2.2-TI2V-5B-GGUFopenQuantStack●Apache 2.0Text to video↓ 30K★ 203bge-multilingual-gemma2openBAAI●Gemma Terms of UseEmbeddings↓ 1.4M★ 203Meta logobart-largeopenfacebook●Apache 2.0Embeddings↓ 145.7K★ 202wan-ggufopencalcuis●Apache 2.0Text to video↓ 20.3K★ 198NeoBERTopenchandar-lab●MITEmbeddings↓ 33.2K★ 197z-image-turbo-flow-dpoopenF16●Apache 2.0Embeddings★ 196DarkBERTopens2w-ai●CC BY-NC 4.0Masked language model↓ 86★ 195chinese-bert-wwm-extopenhfl●Apache 2.0Masked language model↓ 9.6K★ 194FastHunyuanopenFastVideo●otherText to video↓ 16★ 192HunyuanVideo-ggufopencity96●otherText to video↓ 4.3K★ 190Wan2.1-T2V-14B-ggufopencity96●Apache 2.0Text to video↓ 23.2K★ 190vdn-minimax-h3openOpenVDN●otherText to video★ 190jina-embeddings-v5-text-smallopenjinaai●CC BY-NC 4.0Embeddings↓ 205.1K★ 189Meta logonougat-baseopenfacebook●CC BY-NC 4.0Image to text↓ 123.8K★ 188acestep-v15-xl-turboopenACE-Step●MITText to audio↓ 3.8K★ 187i2vgen-xlopenali-vilab●MITText to video↓ 35.8K★ 185kosmos-2-patch14-224openmicrosoft●MITImage to text↓ 173.6K★ 185Open-Sora-v2openhpcai-tech●Apache 2.0Text to video↓ 545★ 181harrier-oss-v1-270mopenmicrosoft●MITEmbeddings↓ 133.5K★ 180trocr-large-printedopenmicrosoft●Not specifiedImage to text↓ 134.3K★ 180TemporalDiffopenCiaraRowles●OpenRAILText to video★ 178pyramid-flow-minifluxopenrain1011●Apache 2.0Text to video★ 178omnivinciopennvidia●Apache 2.0Embeddings↓ 356★ 178PinkCherry_MiniMax-H3openSexGod1979●Apache 2.0Text to video★ 178distilroberta-baseopendistilbert●Apache 2.0Masked language model↓ 1.8M★ 177manga-ocr-baseopenkha-white●Apache 2.0Image to text↓ 488.9K★ 176musicgen-songstarter-v0.2opennateraw●CC BY-NC 4.0Text to audio↓ 25★ 170llama-embed-nemotron-8bopennvidia●otherEmbeddings↓ 27.7K★ 169HunyuanVideo-Foleyopentencent●otherText to audio↓ 271★ 168chinese-macbert-baseopenhfl●Apache 2.0Masked language model↓ 38K★ 167Meta logomusicgen-mediumopenfacebook●CC BY-NC 4.0Text to audio↓ 2M★ 164trocr-large-handwrittenopenmicrosoft●Not specifiedImage to text↓ 233.7K★ 162Qwen logoMiniMax-H3-Fun-Controlnet-Unionopenalibaba-pai●otherText to video↓ 4.3K★ 162JoyAI-Echoopenjdopensource●otherText to video↓ 8K★ 161potat1opencamenduru●Not specifiedText to video↓ 37★ 160FireRed-OCRopenFireRedTeam●Apache 2.0Image to text↓ 2.4K★ 158Google logobert-base-multilingual-uncasedopengoogle-bert●Apache 2.0Masked language model↓ 4.9M★ 158Wan2.2-TI2V-5B-DiffusersopenWan-AI●Apache 2.0Text to video↓ 116.1K★ 148Google logobert-large-uncasedopengoogle-bert●Apache 2.0Masked language model↓ 2.5M★ 147harrier-oss-v1-27bopenmicrosoft●MITEmbeddings↓ 12.6K★ 145Wan2.2-T2V-A14B-DiffusersopenWan-AI●Apache 2.0Text to video↓ 114.8K★ 144Linq-Embed-MistralopenLinq-AI-Research●CC BY-NC 4.0Embeddings↓ 15.2K★ 142albert-base-v2openalbert●Apache 2.0Masked language model↓ 444.8K★ 142MuseVopenTMElyralab●CreativeML OpenRAIL-MText to video★ 138llava-phi-3-mini-ggufopenxtuner●Not specifiedImage to text↓ 1.8K★ 137AudioXopenHKUSTAudio●CC BY-NC 4.0Text to audio★ 135prot_bertopenRostlab●Not specifiedMasked language model↓ 299.6K★ 134Falcon-OCRopentiiuae●Apache 2.0Image to text↓ 4K★ 121donut-base-finetuned-cord-v2opennaver-clova-ix●MITImage to text↓ 27.5K★ 120nemotron-ocr-v1opennvidia●otherImage to text↓ 74★ 120NSFW_MMaudioopenphazei●MITText to audio★ 113TangoFluxopendeclare-lab●Not specifiedText to audio↓ 1.8K★ 112ernie-3.0-base-zhopennghuyong●Not specifiedMasked language model↓ 3.7K★ 112git-baseopenmicrosoft●MITImage to text↓ 12.7K★ 111LFM2.5-Encoder-350MopenLiquidAI●otherMasked language model↓ 5.9K★ 109InLegalBERTopenlaw-ai●MITMasked language model↓ 12.9K★ 107git-large-cocoopenmicrosoft●MITImage to text↓ 3.2K★ 106mmBERT-smallopenjhu-clsp●MITMasked language model↓ 84.8K★ 105PP-OCRv6_medium_det_safetensorsopenPaddlePaddle●Apache 2.0Image to text↓ 3.9K★ 104LFM2.5-Encoder-230MopenLiquidAI●otherMasked language model↓ 15K★ 103camembert-baseopenalmanach●MITMasked language model↓ 1M★ 102VibeVoice-Large-Q8openFabioSarracino●MITText to audio↓ 665★ 99Meta logomusicgen-stereo-largeopenfacebook●CC BY-NC 4.0Text to audio↓ 4.7K★ 96BiomedNLP-BiomedBERT-base-uncased-abstractopenmicrosoft●MITMasked language model↓ 1.1M★ 95chinese-bert-wwmopenhfl●Apache 2.0Masked language model↓ 262.5K★ 93CodeBERTa-small-v1openhuggingface●Not specifiedMasked language model↓ 30.6K★ 93acestep-v15-xl-baseopenACE-Step●MITText to audio↓ 1.1K★ 91bert-for-patentsopenanferico●Apache 2.0Masked language model↓ 24.3K★ 91stable-audio-3-small-musicopenstabilityai●otherText to audio↓ 15.1K★ 90graphcodebert-baseopenmicrosoft●Not specifiedMasked language model↓ 405.9K★ 90acestep-v15-xl-sftopenACE-Step●MITText to audio↓ 4.2K★ 88uform-gen2-qwen-500mopenunum-cloud●Apache 2.0Image to text↓ 604★ 86granite-vision-3.3-2bopenibm-granite●Apache 2.0Image to text↓ 460.8K★ 85PrismAudioopenFunAudioLLM●MITText to audio★ 82ocr-for-captchaopenkeras-io●CC0 1.0Image to text↓ 51★ 82nougat-latex-baseopenNorm●Apache 2.0Image to text↓ 2K★ 82Google logopix2struct-baseopengoogle●Apache 2.0Image to text↓ 2.2K★ 79marvis-tts-250m-v0.1openMarvis-AI●Apache 2.0Text to audio↓ 2K★ 76PixelUMMopennvidia●otherImage to text★ 75Meta logomusicgen-stereo-melody-largeopenfacebook●CC BY-NC 4.0Text to audio↓ 164★ 73openmusicopenjadechoghari●Not specifiedText to audio↓ 26★ 73PP-OCRv5_server_detopenPaddlePaddle●Apache 2.0Image to text↓ 646.4K★ 73Qwen2.5-VL-7B-Abliterated-Caption-it-GGUFopenmradermacher●Apache 2.0Image to text↓ 5.8K★ 73NSFW_MMaudioopencloud19●MITText to audio★ 69Yue2-3B-GGUFopenaudio-cpp●CC BY-NC 4.0Text to audio↓ 66.6K★ 69acestep-v15-baseopenACE-Step●MITText to audio↓ 13.1K★ 67Qwen logomgp-str-baseopenalibaba-damo●Not specifiedImage to text↓ 101.1K★ 65Qwen2-VL-7B-Captioner-RelaxedopenErtugrul●Apache 2.0Image to text↓ 44★ 64stable-audio-3-small-sfxopenstabilityai●otherText to audio↓ 12.9K★ 63trocr-small-handwrittenopenmicrosoft●Not specifiedImage to text↓ 449.8K★ 63paddleocr-onnxopenmonkt●Apache 2.0Image to text★ 63acestep-captioneropenACE-Step●MITText to audio↓ 30.6K★ 62Zero-To-CAD-Qwen3-VL-2BopenADSKAILab●Apache 2.0Image to text↓ 1.4K★ 59pix2text-mfropenbreezedeus●MITImage to text↓ 5.3K★ 57muskopenxiangjx●CC BY-NC-ND 4.0Image to text★ 57japanese-instructblip-alphaopenstabilityai●otherImage to text↓ 55★ 54MOSS-SoundEffectopenOpenMOSS-Team●Apache 2.0Text to audio↓ 1.7K★ 53musicgen-smallopenXenova●CC BY-NC 4.0Text to audio↓ 2.5K★ 51acestep-v15-sftopenACE-Step●MITText to audio↓ 1.4K★ 51MOSS-SoundEffect-v2.0openOpenMOSS-Team●Apache 2.0Text to audio↓ 594★ 49HeartMuLa-oss-3B-happy-new-yearopenHeartMuLa●Apache 2.0Text to audio↓ 2.1K★ 48acestep-5Hz-lm-4BopenACE-Step●MITText to audio↓ 46.8K★ 47tangoopendeclare-lab●CC BY-NC-SA 4.0Text to audio↓ 17★ 46Meta logomusicgen-stereo-smallopenfacebook●CC BY-NC 4.0Text to audio↓ 1.5K★ 45

Open-model metadata (downloads, likes, license) is sourced from the HuggingFace Hub. Frontier/closed models are listed for reference with links to their developers. See Credits & Data Sources.