Paper Code Benchmarks
Paper, code, and benchmark records that connect research context to buildable AI artifacts.
Focused lists make the catalog useful immediately while mirror hosting remains selective and reviewed.
- Multi-Source AI Popular non-Hugging Face records from ModelScope, GitHub, arXiv, OpenML, Zenodo, Dataverse, DataCite, and other indexed open-source AI sources.
- New Open Source Recently updated public open AI artifacts across every indexed source.
How this ranks. The order uses the recorded signals described above. Runtime and verification details live on each model’s record. Self-reported evidence has no trust or ranking impact.
Mirror candidate means the files still live upstream, not on our servers yet. Hosted files do not establish a complete runnable model. Download counts, where recorded, are downloads on Hugging Face.
Showing stale catalog ·
| Type | Model | Recorded size | Downloads | Updated |
|---|---|---|---|---|
Qwen3 Embedding 0.6BQwen/Qwen3-Embedding-0.6BThe catalog lists this model for checking whether two sentences mean similar things. Catalog sources: license label, publisher tags, task label.Content controls: not assessed.DetailsThe catalog lists this model for checking whether two sentences mean similar things.Source: Qwen on Hugging Face. File format: Safetensors.
| 1.21 GB | 10,189,053 downloads on Hugging Face | 2026-04-20 | |
gpt oss 20Bopenai/gpt-oss-20bThe catalog lists this model for having conversations. Catalog sources: license label, publisher tags, task label.Content controls: not assessed.DetailsThe catalog lists this model for having conversations.Source: openai on Hugging Face. File format: BIN, Safetensors.
| 41.3 GB | 7,000,889 downloads on Hugging Face | 2025-08-26 | |
Kokoro 82Mhexgrad/Kokoro-82MThe catalog lists this model for turning text into speech. Catalog sources: license label, task label.Content controls: not assessed.DetailsThe catalog lists this model for turning text into speech.Source: hexgrad on Hugging Face. File format: PTH, PT.
| 363.3 MB | 15,479,373 downloads on Hugging Face | 2025-04-10 | |
parakeet unified en 0.6Bhandy-computer/parakeet-unified-en-0.6b-ggufThe catalog lists this model for transcribing speech. Catalog sources: license label, task label.Content controls: not assessed.DetailsThe catalog lists this model for transcribing speech.Source: handy-computer on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 477.3 MB | 1,560,031 downloads on Hugging Face | 2026-09-18 | |
Qwen2.5 3BQwen/Qwen2.5-3B-InstructThe catalog lists this model for having conversations. Catalog sources: license label, publisher tags, task label.Content controls: not assessed.DetailsThe catalog lists this model for having conversations.Source: Qwen on Hugging Face. File format: Safetensors.
| 6.17 GB | 5,284,682 downloads on Hugging Face | 2026-09-20 | |
robertuito sentiment analysispysentimiento/robertuito-sentiment-analysisThe catalog lists this model for sorting text into categories. Catalog sources: task label.Content controls: not assessed.DetailsThe catalog lists this model for sorting text into categories.Source: pysentimiento on Hugging Face. File format: Safetensors, BIN, H5.
| 1.31 GB | 1,085,789 downloads on Hugging Face | 2026-09-20 | |
tiny random OPTForCausalLMpeft-internal-testing/tiny-random-OPTForCausalLMThe catalog lists this model for generating text. Catalog sources: task label.Content controls: not assessed.DetailsThe catalog lists this model for generating text.Source: peft-internal-testing on Hugging Face. File format: Safetensors.
| 3.26 MB | 1,068,702 downloads on Hugging Face | 2026-09-20 | |
gemma 4 31B itgoogle/gemma-4-31B-itThe catalog lists this model for generating text from images and text. Catalog sources: license label, task label.Content controls: not assessed.DetailsThe catalog lists this model for generating text from images and text.See the publisher’s description →Source: google on Hugging Face. File format: Safetensors.
| 62.6 GB | 10,937,003 downloads on Hugging Face | 2026-07-20 | |
DeepSeek R1deepseek-ai/DeepSeek-R1The catalog lists this model for having conversations. Catalog sources: license label, publisher tags, task label.Content controls: not assessed.DetailsThe catalog lists this model for having conversations.Source: deepseek-ai on Hugging Face. File format: Safetensors.
| 688.6 GB | 7,476,490 downloads on Hugging Face | 2025-03-27 | |
DeepSeek V4 Flashdeepseek-ai/DeepSeek-V4-FlashThe catalog lists this model for generating text. Catalog sources: license label, task label.Content controls: not assessed.DetailsThe catalog lists this model for generating text.Source: deepseek-ai on Hugging Face. File format: Safetensors.
| 159.6 GB | 1,934,541 downloads on Hugging Face | 2026-06-22 | |
gpt oss 120Bopenai/gpt-oss-120bThe catalog lists this model for having conversations. Catalog sources: license label, publisher tags, task label.Content controls: not assessed.DetailsThe catalog lists this model for having conversations.Source: openai on Hugging Face. File format: BIN, Safetensors.
| 195.8 GB | 4,043,429 downloads on Hugging Face | 2025-08-26 | |
DeepSeek R1 0528deepseek-ai/DeepSeek-R1-0528The catalog lists this model for having conversations. Catalog sources: license label, publisher tags, task label.Content controls: not assessed.DetailsThe catalog lists this model for having conversations.Source: deepseek-ai on Hugging Face. File format: Safetensors.
| 688.6 GB | 3,982,017 downloads on Hugging Face | 2025-05-29 | |
GLM 5 FP8zai-org/GLM-5-FP8The catalog lists this model for having conversations. Catalog sources: license label, publisher tags, task label.Content controls: not assessed.DetailsThe catalog lists this model for having conversations.Source: zai-org on Hugging Face. File format: Safetensors.
| 756.2 GB | 2,275,490 downloads on Hugging Face | 2026-04-05 | |
Qwen3 30B A3BQwen/Qwen3-30B-A3BThe catalog lists this model for having conversations. Catalog sources: license label, publisher tags, task label.Content controls: not assessed.DetailsThe catalog lists this model for having conversations.Source: Qwen on Hugging Face. File format: Safetensors.
| 61.1 GB | 2,788,018 downloads on Hugging Face | 2025-07-26 | |
Qwen2 VL 7BQwen/Qwen2-VL-7B-InstructThe catalog lists this model for generating text from images and text. Catalog sources: license label, task label.Content controls: not assessed.DetailsThe catalog lists this model for generating text from images and text.See the publisher’s description →Source: Qwen on Hugging Face. File format: Safetensors.
| 16.6 GB | 1,823,883 downloads on Hugging Face | 2025-02-06 | |
DeepSeek V3 0324deepseek-ai/DeepSeek-V3-0324The catalog lists this model for having conversations. Catalog sources: license label, publisher tags, task label.Content controls: not assessed.DetailsThe catalog lists this model for having conversations.Source: deepseek-ai on Hugging Face. File format: Safetensors.
| 688.6 GB | 1,171,847 downloads on Hugging Face | 2025-03-27 | |
deberta v3 basemicrosoft/deberta-v3-baseThe catalog lists this model for filling in missing words in text. Catalog sources: license label, task label.Content controls: not assessed.DetailsThe catalog lists this model for filling in missing words in text.Source: microsoft on Hugging Face. File format: BIN, H5.
| 1.85 GB | 2,562,101 downloads on Hugging Face | 2022-09-22 | |
GLM 5.1 FP8zai-org/GLM-5.1-FP8The catalog lists this model for having conversations. Catalog sources: license label, publisher tags, task label.Content controls: not assessed.DetailsThe catalog lists this model for having conversations.Source: zai-org on Hugging Face. File format: Safetensors.
| 756.2 GB | 1,005,592 downloads on Hugging Face | 2026-04-16 | |
timesfm 2.5 200m pytorchgoogle/timesfm-2.5-200m-pytorchThe catalog lists this model for predicting how numbers may change over time. Catalog sources: license label, task label.Content controls: not assessed.DetailsThe catalog lists this model for predicting how numbers may change over time.See the publisher’s description →Source: google on Hugging Face. File format: Safetensors.
| 925.2 MB | 1,853,260 downloads on Hugging Face | 2025-10-02 | |
wav2vec2 basefacebook/wav2vec2-baseThe catalog does not give enough information to describe what this model is for. Catalog sources: license label.Content controls: not assessed.DetailsThe catalog does not give enough information to describe what this model is for.See the publisher’s description →Source: facebook on Hugging Face. File format: BIN.
| 380.3 MB | 2,434,701 downloads on Hugging Face | 2021-12-28 | |
deberta v3 largemicrosoft/deberta-v3-largeThe catalog lists this model for filling in missing words in text. Catalog sources: license label, task label.Content controls: not assessed.DetailsThe catalog lists this model for filling in missing words in text.Source: microsoft on Hugging Face. File format: BIN, H5.
| 3.18 GB | 1,163,028 downloads on Hugging Face | 2023-03-19 | |
wav2vec2 lv 60 espeak cv ftfacebook/wav2vec2-lv-60-espeak-cv-ftThe catalog lists this model for transcribing speech. Catalog sources: license label, task label.Content controls: not assessed.DetailsThe catalog lists this model for transcribing speech.Source: facebook on Hugging Face. File format: BIN.
| 1.26 GB | 1,311,735 downloads on Hugging Face | 2023-10-31 | |
bigvgan v2 22khz 80band 256xnvidia/bigvgan_v2_22khz_80band_256xThe catalog lists this model for transforming audio. Catalog sources: license label, task label.Content controls: not assessed.DetailsThe catalog lists this model for transforming audio.See the publisher’s description →Source: nvidia on Hugging Face. File format: PT.
| 3.79 GB | 1,629,010 downloads on Hugging Face | 2024-09-05 | |
fnet basegoogle/fnet-baseThe catalog does not give enough information to describe what this model is for. Catalog sources: license label.Content controls: not assessed.DetailsThe catalog does not give enough information to describe what this model is for.See the publisher’s description →Source: google on Hugging Face. File format: BIN.
| 768.3 MB | 1,239,416 downloads on Hugging Face | 2024-02-29 | |
nsfw image detectionFalconsai/nsfw_image_detectionThe catalog lists this model for labeling images. Catalog sources: license label, task label.Content controls: not assessed.DetailsThe catalog lists this model for labeling images.Source: Falconsai on Hugging Face. File format: PT, Safetensors, BIN.
| 1.46 GB | 9,792,328 downloads on Hugging Face | 2026-09-07 | |
Bio ClinicalBERTemilyalsentzer/Bio_ClinicalBERTThe catalog lists this model for filling in missing words in text. Catalog sources: license label, task label.Content controls: not assessed.DetailsThe catalog lists this model for filling in missing words in text.Source: emilyalsentzer on Hugging Face.
| 2.72 GB | 4,426,627 downloads on Hugging Face | 2024-12-03 | |
wav2vec2 large xlsr 53 russianjonatasgrosman/wav2vec2-large-xlsr-53-russianThe catalog lists this model for transcribing speech. Catalog sources: license label, task label.Content controls: not assessed.DetailsThe catalog lists this model for transcribing speech.Source: jonatasgrosman on Hugging Face.
| 4.05 GB | 3,113,503 downloads on Hugging Face | 2022-12-14 | |
wav2vec2 large xlsr 53 portuguesejonatasgrosman/wav2vec2-large-xlsr-53-portugueseThe catalog lists this model for transcribing speech. Catalog sources: license label, task label.Content controls: not assessed.DetailsThe catalog lists this model for transcribing speech.Source: jonatasgrosman on Hugging Face.
| 3.72 GB | 3,203,416 downloads on Hugging Face | 2022-12-14 | |
wav2vec2 large xlsr 53 dutchjonatasgrosman/wav2vec2-large-xlsr-53-dutchThe catalog lists this model for transcribing speech. Catalog sources: license label, task label.Content controls: not assessed.DetailsThe catalog lists this model for transcribing speech.Source: jonatasgrosman on Hugging Face.
| 3.93 GB | 4,162,465 downloads on Hugging Face | 2022-12-14 | |
wav2vec2 large xlsr 53 polishjonatasgrosman/wav2vec2-large-xlsr-53-polishThe catalog lists this model for transcribing speech. Catalog sources: license label, task label.Content controls: not assessed.DetailsThe catalog lists this model for transcribing speech.Source: jonatasgrosman on Hugging Face.
| 4.17 GB | 4,722,399 downloads on Hugging Face | 2022-12-14 | |
wav2vec2 indonesian javanese sundaneseindonesian-nlp/wav2vec2-indonesian-javanese-sundaneseThe catalog lists this model for transcribing speech. Catalog sources: license label, task label.Content controls: not assessed.DetailsThe catalog lists this model for transcribing speech.Source: indonesian-nlp on Hugging Face. File format: BIN.
| 3.5 GB | 4,206,582 downloads on Hugging Face | 2022-08-19 | |
vocos mel 24khzcharactr/vocos-mel-24khzThe catalog does not give enough information to describe what this model is for. Catalog sources: license label.Content controls: not assessed.DetailsThe catalog does not give enough information to describe what this model is for.See the publisher’s description →Source: charactr on Hugging Face. File format: BIN.
| 54.4 MB | 2,630,105 downloads on Hugging Face | 2023-10-17 | |
bert tinyprajjwal1/bert-tinyThe catalog does not give enough information to describe what this model is for. Catalog sources: license label.Content controls: not assessed.DetailsThe catalog does not give enough information to describe what this model is for.See the publisher’s description →Source: prajjwal1 on Hugging Face. File format: BIN.
| 17.8 MB | 1,164,801 downloads on Hugging Face | 2021-10-27 | |
wav2vec2 xls r 300m bengaliarijitx/wav2vec2-xls-r-300m-bengaliThe catalog lists this model for transcribing speech. Catalog sources: license label, task label.Content controls: not assessed.DetailsThe catalog lists this model for transcribing speech.Source: arijitx on Hugging Face. File format: BIN.
| 4.8 GB | 1,452,237 downloads on Hugging Face | 2022-03-23 | |
vakyansh wav2vec2 tamil tam 250Harveenchadha/vakyansh-wav2vec2-tamil-tam-250The catalog lists this model for transcribing speech. Catalog sources: license label, task label.Content controls: not assessed.DetailsThe catalog lists this model for transcribing speech.Source: Harveenchadha on Hugging Face. File format: BIN.
| 377.7 MB | 2,229,088 downloads on Hugging Face | 2021-09-22 | |
clip vit base patch32openai/clip-vit-base-patch32The catalog lists this model for classifying images with supplied labels. Catalog sources: task label.Content controls: not assessed.DetailsThe catalog lists this model for classifying images with supplied labels.Source: openai on Hugging Face. File format: BIN, H5.
| 1.82 GB | 21,776,108 downloads on Hugging Face | 2024-02-29 | |
DeepSeek V3deepseek-ai/DeepSeek-V3The catalog lists this model for having conversations. Catalog sources: publisher tags, task label.Content controls: not assessed.DetailsThe catalog lists this model for having conversations.Source: deepseek-ai on Hugging Face. File format: Safetensors.
| 688.6 GB | 1,131,639 downloads on Hugging Face | 2025-03-27 | |
docling modelsdocling-project/docling-modelsThe catalog does not give enough information to describe what this model is for. Catalog source: unknown.Content controls: not assessed.DetailsThe catalog does not give enough information to describe what this model is for.Source: docling-project on Hugging Face. File format: Safetensors.
| 358.2 MB | 1,908,604 downloads on Hugging Face | 2025-12-03 | |
wav2vec2 large xlsr 53 japanesejonatasgrosman/wav2vec2-large-xlsr-53-japaneseThe catalog lists this model for transcribing speech. Catalog sources: license label, task label.Content controls: not assessed.DetailsThe catalog lists this model for transcribing speech.Source: jonatasgrosman on Hugging Face. File format: BIN.
| 2.54 GB | 6,095,794 downloads on Hugging Face | 2022-12-14 | |
wav2vec2 large xlsr 53 arabicjonatasgrosman/wav2vec2-large-xlsr-53-arabicThe catalog lists this model for transcribing speech. Catalog sources: license label, task label.Content controls: not assessed.DetailsThe catalog lists this model for transcribing speech.Source: jonatasgrosman on Hugging Face. File format: BIN.
| 2.52 GB | 3,550,653 downloads on Hugging Face | 2022-12-14 | |
wav2vec2 large xlsr 53 chinese zh cnjonatasgrosman/wav2vec2-large-xlsr-53-chinese-zh-cnThe catalog lists this model for transcribing speech. Catalog sources: license label, task label.Content controls: not assessed.DetailsThe catalog lists this model for transcribing speech.Source: jonatasgrosman on Hugging Face. File format: BIN.
| 2.55 GB | 1,545,141 downloads on Hugging Face | 2022-12-14 | |
wav2vec2 large xlsr 53 persianjonatasgrosman/wav2vec2-large-xlsr-53-persianThe catalog lists this model for transcribing speech. Catalog sources: license label, task label.Content controls: not assessed.DetailsThe catalog lists this model for transcribing speech.Source: jonatasgrosman on Hugging Face. File format: BIN.
| 2.52 GB | 2,547,784 downloads on Hugging Face | 2022-12-14 | |
wav2vec2 large xlsr 53 hungarianjonatasgrosman/wav2vec2-large-xlsr-53-hungarianThe catalog lists this model for transcribing speech. Catalog sources: license label, task label.Content controls: not assessed.DetailsThe catalog lists this model for transcribing speech.Source: jonatasgrosman on Hugging Face. File format: BIN.
| 2.52 GB | 3,437,587 downloads on Hugging Face | 2022-12-14 | |
wav2vec2 large xlsr 53 greekjonatasgrosman/wav2vec2-large-xlsr-53-greekThe catalog lists this model for transcribing speech. Catalog sources: license label, task label.Content controls: not assessed.DetailsThe catalog lists this model for transcribing speech.Source: jonatasgrosman on Hugging Face. File format: BIN.
| 2.52 GB | 3,885,031 downloads on Hugging Face | 2022-12-14 | |
wav2vec2 large xlsr 53 teluguanuragshas/wav2vec2-large-xlsr-53-teluguThe catalog lists this model for transcribing speech. Catalog sources: license label, task label.Content controls: not assessed.DetailsThe catalog lists this model for transcribing speech.Source: anuragshas on Hugging Face. File format: BIN.
| 2.52 GB | 2,801,450 downloads on Hugging Face | 2021-07-05 | |
wav2vec2 xlsr nepaligagan3012/wav2vec2-xlsr-nepaliThe catalog lists this model for transcribing speech. Catalog sources: license label, task label.Content controls: not assessed.DetailsThe catalog lists this model for transcribing speech.Source: gagan3012 on Hugging Face. File format: PT, BIN.
| 5.01 GB | 1,321,648 downloads on Hugging Face | 2021-07-06 | |
wav2vec2 large xlsr malayalamgvs/wav2vec2-large-xlsr-malayalamThe catalog lists this model for transcribing speech. Catalog sources: license label, task label.Content controls: not assessed.DetailsThe catalog lists this model for transcribing speech.Source: gvs on Hugging Face. File format: BIN.
| 2.52 GB | 1,186,777 downloads on Hugging Face | 2021-07-06 | |
wav2vec2 large xlsr 53 finnishjonatasgrosman/wav2vec2-large-xlsr-53-finnishThe catalog lists this model for transcribing speech. Catalog sources: license label, task label.Content controls: not assessed.DetailsThe catalog lists this model for transcribing speech.Source: jonatasgrosman on Hugging Face. File format: BIN.
| 2.52 GB | 1,879,157 downloads on Hugging Face | 2022-12-14 | |
wav2vec2 large xlsr catalasoftcatala/wav2vec2-large-xlsr-catalaThe catalog lists this model for transcribing speech. Catalog sources: license label, task label.Content controls: not assessed.DetailsThe catalog lists this model for transcribing speech.Source: softcatala on Hugging Face. File format: BIN.
| 2.52 GB | 1,131,985 downloads on Hugging Face | 2022-02-08 | |
wav2vec2 large xlsr 53 estoniananton-l/wav2vec2-large-xlsr-53-estonianThe catalog lists this model for transcribing speech. Catalog sources: license label, task label.Content controls: not assessed.DetailsThe catalog lists this model for transcribing speech.Source: anton-l on Hugging Face. File format: BIN.
| 2.52 GB | 989,073 downloads on Hugging Face | 2021-07-05 |