Compare models
Organisation, model, parameter count, architectural context length and licence, from the model register. Click a column heading to sort. Parameter counts are exact; context length is max_position_embeddings — the architectural maximum, not necessarily what a provider serves. A blank cell was not sourced and has not been guessed.
What is in this table. Releases only — the same default view as the register. Displayed figures may be shortened; the CSV and JSON keep the exact numbers. A further 93 derivative records (quantisations and conversions) are in those downloads and not in this table.
| 01-ai | Yi-1.5-34B | 34.4B | 4K | apache-2.0 |
| 01-ai | Yi-1.5-34B-Chat | 34.4B | 4K | apache-2.0 |
| 01-ai | Yi-1.5-6B | 6.1B | 4K | apache-2.0 |
| 01-ai | Yi-1.5-9B | 8.8B | 4K | apache-2.0 |
| 01-ai | Yi-1.5-9B-Chat | 8.8B | 4K | apache-2.0 |
| 01-ai | Yi-1.5-9B-Chat-16K | 8.8B | 16K | apache-2.0 |
| 01-ai | Yi-34B | 34.4B | 4K | apache-2.0 |
| 01-ai | Yi-34B-200K | 34.4B | 195K | apache-2.0 |
| 01-ai | Yi-34B-Chat | 34.4B | 4K | apache-2.0 |
| 01-ai | Yi-6B | 6.1B | 4K | apache-2.0 |
| 01-ai | Yi-6B-200K | 6.1B | 195K | apache-2.0 |
| 01-ai | Yi-6B-Chat | 6.1B | 4K | apache-2.0 |
| 01-ai | Yi-Coder-9B-Chat | 8.8B | 128K | apache-2.0 |
| akatz-ai | MiniMax-H3-Character-Swap-LoRA | — | — | other |
| Alissonerdx | BFS-Best-Face-Swap | — | — | mit |
| Alissonerdx | Minimax-H3-ComfyUI | — | — | other |
| allenai | AstaBrief_8B | — | 40K | apache-2.0 |
| allenai | longformer-base-4096 | — | 4K | apache-2.0 |
| allenai | OLMo-2-0425-1B | 1.5B | 4K | apache-2.0 |
| allenai | OLMo-2-1124-7B | 7.3B | 4K | apache-2.0 |
| allenai | Olmo-3-1025-7B | 7.3B | 64K | apache-2.0 |
| allenai | Olmo-3-7B-Instruct | 7.3B | 64K | apache-2.0 |
| allenai | Olmo-3-7B-Think | 7.3B | 64K | apache-2.0 |
| allenai | olmOCR-2-7B-1025 | 8.3B | 125K | apache-2.0 |
| allenai | olmOCR-7B-0225-preview | 8.3B | 32K | apache-2.0 |
| allenai | OLMoE-1B-7B-0125-Instruct | 6.9B | 4K | apache-2.0 |
| allenai | OLMoE-1B-7B-0924 | 6.9B | 4K | apache-2.0 |
| allenai | scibert_scivocab_uncased | — | 512 | — |
| allenai | specter2_base | — | 512 | apache-2.0 |
| allenai | unifiedqa-t5-small | — | — | — |
| allenai | wildguard | 7.2B | — | apache-2.0 |
| amazon | ALoDLM-8B | 8.2B | 40K | cc-by-nc-4.0 |
| amazon | bort | — | 512 | — |
| amazon | chronos-2 | 119M | — | apache-2.0 |
| amazon | chronos-bolt-base | 205M | — | apache-2.0 |
| amazon | chronos-bolt-mini | 21M | — | apache-2.0 |
| amazon | chronos-bolt-small | 48M | — | apache-2.0 |
| amazon | chronos-bolt-tiny | 9M | — | apache-2.0 |
| amazon | chronos-t5-base | 201M | — | apache-2.0 |
| amazon | chronos-t5-large | 709M | — | apache-2.0 |
| amazon | chronos-t5-mini | 20M | — | apache-2.0 |
| amazon | chronos-t5-small | 46M | — | apache-2.0 |
| amazon | chronos-t5-tiny | 8M | — | apache-2.0 |
| amazon | GDN-primed-HQwen3-8B-Instruct | 8.5B | 128K | apache-2.0 |
| amazon | GKA-primed-HQwen3-32B-Reasoner | 34.1B | 128K | apache-2.0 |
| amazon | MistralLite | — | 32K | apache-2.0 |
| amazon | Titan-text-embeddings-v2 | — | — | other |
| answerdotai | ModernBERT-base | 150M | 8K | apache-2.0 |
| apple | aimv2-large-patch14-224-lit | 437M | 77 | apple-amlr |
| apple | coreml-depth-anything-v2-small | — | — | apache-2.0 |
| apple | DepthPro | — | — | apple-amlr |
| apple | DepthPro-hf | 952M | — | apple-amlr |
| apple | DFN2B-CLIP-ViT-B-16 | — | — | apple-amlr |
| apple | DFN2B-CLIP-ViT-L-14 | — | 77 | apple-amlr |
| apple | DFN2B-CLIP-ViT-L-14-39B | — | 77 | apple-amlr |
| apple | DFN5B-CLIP-ViT-H-14 | — | 77 | apple-amlr |
| apple | DFN5B-CLIP-ViT-H-14-378 | — | 77 | apple-amlr |
| apple | FastVLM-0.5B | 759M | 32K | apple-amlr |
| apple | LensVLM-9B | 9.4B | 256K | apple-amlr |
| apple | MobileCLIP-S1-OpenCLIP | — | — | apple-amlr |
| apple | MobileCLIP-S2-OpenCLIP | — | — | apple-amlr |
| apple | mobilevit-small | — | — | other |
| apple | mobilevit-xx-small | — | — | other |
| apple | OpenELM-1_1B-Instruct | 1.1B | — | apple-amlr |
| argmaxinc | whisperkit-coreml | — | — | mit |
| autogluon | chronos-2 | 119M | — | apache-2.0 |
| autogluon | chronos-2-small | 28M | — | apache-2.0 |
| autogluon | chronos-bolt-small | 48M | — | apache-2.0 |
| autotrust | GEV-26B-Decide | 25.8B | 256K | apache-2.0 |
| autotrust | JEV-27B-VL | 27.8B | 256K | apache-2.0 |
| autotrust | JEV-35B | 36.0B | 256K | apache-2.0 |
| autotrust | JEV-9B | 9.0B | 256K | apache-2.0 |
| BAAI | bge-base-en-v1.5 | 109M | 512 | mit |
| BAAI | bge-large-en-v1.5 | 335M | 512 | mit |
| BAAI | bge-m3 | — | 8K | mit |
| BAAI | bge-reranker-base | 278M | 514 | mit |
| BAAI | bge-reranker-v2-m3 | 568M | 8K | apache-2.0 |
| BAAI | bge-small-en-v1.5 | 33M | 512 | mit |
| BAAI | bge-small-zh-v1.5 | 24M | 512 | mit |
| baidu | ERNIE-4.5-0.3B-Base-PT | 361M | 128K | apache-2.0 |
| baidu | ERNIE-4.5-0.3B-PT | 361M | 128K | apache-2.0 |
| baidu | ERNIE-4.5-21B-A3B-PT | 21.9B | 128K | apache-2.0 |
| baidu | ERNIE-4.5-21B-A3B-Thinking | 21.8B | 128K | apache-2.0 |
| baidu | ERNIE-4.5-300B-A47B-PT | 300.5B | 128K | apache-2.0 |
| baidu | ERNIE-4.5-VL-28B-A3B-PT | 29.4B | 128K | apache-2.0 |
| baidu | ERNIE-4.5-VL-28B-A3B-Thinking | 29.7B | 128K | apache-2.0 |
| baidu | ERNIE-4.5-VL-424B-A47B-Base-PT | 423.5B | 128K | apache-2.0 |
| baidu | ERNIE-4.5-VL-424B-A47B-PT | 423.5B | 128K | apache-2.0 |
| baidu | ERNIE-Image | 8.0B | — | apache-2.0 |
| baidu | ERNIE-Image-Turbo | 8.0B | — | apache-2.0 |
| baidu | Qianfan-OCR | 4.7B | 32K | apache-2.0 |
| baidu | Unlimited-OCR | 3.3B | 32K | mit |
| bigcode | gpt_bigcode-santacoder | 1.1B | — | openrail |
| bigcode | santacoder | — | — | bigcode-openrail-m |
| bigcode | santacoder-fast-inference | — | — | openrail |
| bigcode | starcoder | 15.8B | — | bigcode-openrail-m |
| bigcode | starcoder2-15b | 16.0B | 16K | bigcode-openrail-m |
| bigcode | starcoder2-15b-instruct-v0.1 | 16.0B | 16K | bigcode-openrail-m |
| bigcode | starcoder2-3b | 3.0B | 16K | bigcode-openrail-m |
| bigcode | starcoder2-7b | 7.2B | 16K | bigcode-openrail-m |
| bigcode | starcoderbase | — | — | bigcode-openrail-m |
| bigcode | starcoderbase-1b | 1.1B | — | bigcode-openrail-m |
| bigcode | starcoderbase-7b | 7.5B | — | bigcode-openrail-m |
| bigcode | starpii | — | — | — |
| bigcode | tiny_starcoder_py | 164M | — | bigcode-openrail-m |
| Bingsu | adetailer | — | — | apache-2.0 |
| black-forest-labs | flux-3-image-klein | 5.5B | — | other |
| black-forest-labs | flux-3-image-klein-comfy | — | — | other |
| black-forest-labs | FLUX.1-dev | 11.9B | — | other |
| Cactus-Compute | needle3 | — | 8K | apache-2.0 |
| Comfy-Org | Krea-2 | — | — | other |
| Comfy-Org | MiniMax-H3 | — | — | other |
| Comfy-Org | MOSS-Image | — | — | apache-2.0 |
| Comfy-Org | Qwen-Image-2.1 | — | — | other |
| Comfy-Org | stable-diffusion-v1-5-archive | — | — | creativeml-openrail-m |
| Comfy-Org | Wan_2.1_ComfyUI_repackaged | — | — | apache-2.0 |
| Comfy-Org | Wan_2.2_ComfyUI_Repackaged | — | — | apache-2.0 |
| Comfy-Org | YuE2 | — | — | cc-by-nc-4.0 |
| Comfy-Org | z_image_turbo | — | — | apache-2.0 |
| convaiinnovations | laya | 421M | — | apache-2.0 |
| ConwayResearch | Underdog-Saluki-27B-1.0 | — | — | apache-2.0 |
| coqui | XTTS-v2 | — | — | other |
| cross-encoder | ms-marco-MiniLM-L4-v2 | 19M | 512 | apache-2.0 |
| cross-encoder | ms-marco-MiniLM-L6-v2 | 23M | 512 | apache-2.0 |
| datasocietyco | bge-base-en-v1.5-course-recommender-v5 | 109M | 512 | — |
| deepseek-ai | deepseek-coder-7b-instruct-v1.5 | 6.9B | 4K | other |
| deepseek-ai | DeepSeek-Coder-V2-Lite-Instruct | 15.7B | 160K | other |
| deepseek-ai | DeepSeek-OCR | 3.3B | 8K | mit |
| deepseek-ai | DeepSeek-OCR-2 | 3.4B | 8K | apache-2.0 |
| deepseek-ai | DeepSeek-R1 | 684.5B | 160K | mit |
| deepseek-ai | DeepSeek-R1-0528-Qwen3-8B | 8.2B | 128K | mit |
| deepseek-ai | DeepSeek-R1-Distill-Qwen-1.5B | 1.8B | 128K | mit |
| deepseek-ai | DeepSeek-V3 | 684.5B | 160K | — |
| deepseek-ai | DeepSeek-V3-0324 | 684.5B | 160K | mit |
| deepseek-ai | DeepSeek-V3.2 | 685.4B | 160K | mit |
| deepseek-ai | DeepSeek-V4-Flash | 290.9B | 1M | mit |
| deepseek-ai | DeepSeek-V4-Flash-0731 | 304.2B | 1M | mit |
| deepseek-ai | DeepSeek-V4-Flash-DSpark | 165.3B | 1M | mit |
| deepseek-ai | DeepSeek-V4-Flash-Vision-Exp | 304.6B | 1M | mit |
| deepseek-ai | DeepSeek-V4.1-Flash | 763.2B | 1M | mit |
| deepseek-ai | DeepSeek-V4.1-Flash-1017 | 763.2B | 1M | mit |
| distilbert | distilbert-base-uncased | 67M | 512 | apache-2.0 |
| dphn | dolphin-2.9.1-yi-1.5-34b | 34.4B | 8K | apache-2.0 |
| contriever | — | 512 | — | |
| dinov3-vitl16-pretrain-lvd1689m | 303M | — | other | |
| esm2_t33_650M_UR50D | 652M | 1K | mit | |
| opt-125m | — | 2K | other | |
| sam3 | 860M | — | other | |
| sam3.1 | — | — | other | |
| FacebookAI | roberta-base | 125M | 514 | mit |
| FacebookAI | roberta-large | 355M | 514 | mit |
| FacebookAI | xlm-roberta-base | 279M | 514 | mit |
| farbodtavakkoli | OTel-2.0-LLM-31B-IT | 31.3B | 256K | apache-2.0 |
| fastino | GLiNER2.5-Decide | 486M | 512 | apache-2.0 |
| fastino | gliner2.5-multi-v1 | 287M | — | apache-2.0 |
| electra-base-discriminator | — | 512 | apache-2.0 | |
| embeddinggemma-2 | 744M | 256K | apache-2.0 | |
| embeddinggemma-300m | 303M | — | gemma | |
| gemma-3-1b-it | 1000M | — | gemma | |
| gemma-4-12B-it | 12.0B | 256K | apache-2.0 | |
| gemma-4-26B-A4B-it | 25.8B | 256K | apache-2.0 | |
| gemma-4-31B-it | 31.3B | 256K | apache-2.0 | |
| gemma-4-E2B-it | 5.1B | 128K | apache-2.0 | |
| gemma-4-E4B-it | 8.0B | 128K | apache-2.0 | |
| owlv2-base-patch16-ensemble | 155M | — | apache-2.0 | |
| siglip-base-patch16-224 | 203M | — | apache-2.0 | |
| siglip2-base-patch16-224 | 375M | — | apache-2.0 | |
| siglip2-base-patch16-256 | 375M | — | apache-2.0 | |
| siglip2-giant-opt-patch16-384 | 1.9B | — | apache-2.0 | |
| vit-base-patch16-224 | 87M | — | apache-2.0 | |
| google-bert | bert-base-uncased | 110M | 512 | apache-2.0 |
| google-t5 | t5-small | 61M | — | apache-2.0 |
| hexgrad | Kokoro-82M | — | 512 | apache-2.0 |
| ibm-granite | granite-3.3-2b-instruct | 2.5B | 128K | apache-2.0 |
| ibm-granite | granite-4.1-30b | 28.9B | 128K | apache-2.0 |
| ibm-granite | granite-4.1-3b | 3.4B | 128K | apache-2.0 |
| ibm-granite | granite-4.1-8b | 8.8B | 128K | apache-2.0 |
| ibm-granite | granite-docling-258M | 258M | 8K | apache-2.0 |
| ibm-granite | granite-embedding-311m-multilingual-r2 | 312M | 32K | apache-2.0 |
| ibm-granite | granite-embedding-small-english-r2 | 48M | 8K | apache-2.0 |
| ibm-granite | granite-speech-4.1-2b | 2.3B | 2K | apache-2.0 |
| ibm-granite | granite-timeseries-patchtst-fm-r2 | 385M | — | openmdw-1.0 |
| ibm-granite | granite-timeseries-tspulse-r1 | 1M | — | apache-2.0 |
| ibm-granite | granite-timeseries-ttm-r2 | 805,280 | — | apache-2.0 |
| ibm-granite | granite-timeseries-ttm-r3 | 1M | — | apache-2.0 |
| ibm-granite | granite-vision-3.3-2b | 3.0B | 128K | apache-2.0 |
| ibm-granite | granite-vision-4.1-4b | 4.0B | 128K | apache-2.0 |
| internlm | Atria-Dawn-Preview | 753.3B | 1M | mit |
| internlm | Intern-Decision-4B | 4.5B | 256K | apache-2.0 |
| internlm | Intern-S1 | 240.7B | 64K | apache-2.0 |
| internlm | Intern-S1-mini | 8.5B | 64K | apache-2.0 |
| internlm | internlm-chat-7b | — | 2K | — |
| internlm | internlm-xcomposer2-vl-7b | — | 32K | other |
| internlm | internlm2_5-7b-chat | 7.7B | 32K | other |
| internlm | internlm2-1_8b-reward | 1.7B | 32K | other |
| internlm | internlm2-20b | — | 32K | other |
| internlm | internlm2-7b | — | 32K | other |
| internlm | internlm2-base-20b | — | 32K | other |
| internlm | internlm2-base-7b | — | 32K | other |
| internlm | internlm2-chat-20b | 19.9B | 32K | other |
| internlm | internlm2-chat-7b | 7.7B | 32K | other |
| internlm | internlm3-8b-instruct | 8.8B | 32K | apache-2.0 |
| intfloat | multilingual-e5-base | 278M | 514 | mit |
| intfloat | multilingual-e5-large | 560M | 514 | mit |
| intfloat | multilingual-e5-small | 118M | 512 | mit |
| jialinyyzz | humanizer | 12.0B | 256K | apache-2.0 |
| jonatasgrosman | wav2vec2-large-xlsr-53-japanese | — | — | apache-2.0 |
| jonatasgrosman | wav2vec2-large-xlsr-53-portuguese | — | — | apache-2.0 |
| jonatasgrosman | wav2vec2-large-xlsr-53-russian | — | — | apache-2.0 |
| krea | Krea-2-Raw | 12.8B | — | other |
| krea | Krea-2-Turbo | 12.8B | — | other |
| laion | clap-htsat-fused | 154M | 514 | apache-2.0 |
| laion | CLIP-ViT-B-32-laion2B-s34B-b79K | 151M | 77 | mit |
| Lightricks | LTX-2.5 | — | — | other |
| lightx2v | Qwen-Image-2.1-Lightning | — | — | — |
| Mapika | decider-2b | 1.9B | 256K | apache-2.0 |
| meta-llama | Llama-2-7b-chat-hf | 6.7B | — | llama2 |
| meta-llama | Llama-2-7b-hf | 6.7B | — | llama2 |
| meta-llama | Llama-3.1-8B | 8.0B | — | llama3.1 |
| meta-llama | Llama-3.1-8B-Instruct | 8.0B | — | llama3.1 |
| meta-llama | Llama-3.2-1B | 1.2B | — | llama3.2 |
| meta-llama | Llama-3.2-1B-Instruct | 1.2B | — | llama3.2 |
| meta-llama | Llama-3.2-3B | 3.2B | — | llama3.2 |
| meta-llama | Llama-3.2-3B-Instruct | 3.2B | — | llama3.2 |
| meta-llama | Llama-3.3-70B-Instruct | 70.6B | — | llama3.3 |
| meta-llama | Meta-Llama-3-8B-Instruct | 8.0B | — | llama3 |
| meta-llama | Prompt-Guard-86M | 279M | — | llama3.1 |
| microsoft | AesCode-8B | 8.8B | 256K | apache-2.0 |
| microsoft | BiomedNLP-BiomedBERT-base-uncased-abstract | — | 512 | mit |
| microsoft | deberta-v3-base | — | 512 | mit |
| microsoft | deberta-v3-large | — | 512 | mit |
| microsoft | deberta-v3-small | — | 512 | mit |
| microsoft | Florence-2-base | 232M | 1K | mit |
| microsoft | FrogNano-4B-2609 | 4.7B | 256K | mit |
| microsoft | layoutlmv3-base | 125M | 514 | cc-by-nc-sa-4.0 |
| microsoft | mdeberta-v3-base | — | 512 | mit |
| microsoft | Phi-3.5-vision-instruct | 4.1B | 128K | mit |
| microsoft | table-transformer-structure-recognition | 29M | 1K | mit |
| microsoft | tapex-base-finetuned-wikisql | — | 1K | mit |
| microsoft | TRELLIS-image-large | — | — | mit |
| microsoft | TRELLIS.2-4B | — | — | mit |
| microsoft | VibeVoice-1.5B | 2.7B | 64K | mit |
| microsoft | VibeVoice-ASR | 8.7B | 128K | mit |
| microsoft | wavlm-large | — | — | — |
| MiniMaxAI | MiniMax-H3 | 33.1B | — | other |
| mistralai | Devstral-Small-2-24B-Instruct-2512 | 24.0B | 384K | apache-2.0 |
| mistralai | Ministral-3-14B-Instruct-2512 | 13.9B | 256K | apache-2.0 |
| mistralai | Mistral-7B-Instruct-v0.1 | 7.2B | 32K | apache-2.0 |
| mistralai | Mistral-7B-Instruct-v0.2 | 7.2B | 32K | apache-2.0 |
| mistralai | Mistral-7B-Instruct-v0.3 | 7.2B | 32K | apache-2.0 |
| mistralai | Mistral-7B-v0.1 | 7.2B | 32K | apache-2.0 |
| mistralai | Mistral-7B-v0.3 | 7.2B | 32K | apache-2.0 |
| mistralai | Mistral-Nemo-Instruct-2407 | 12.2B | 128K | apache-2.0 |
| mistralai | Mistral-Small-3.1-24B-Instruct-2503 | 24.0B | 128K | apache-2.0 |
| mistralai | Mistral-Small-3.2-24B-Instruct-2506 | 24.0B | 128K | apache-2.0 |
| mistralai | Mixtral-8x7B-Instruct-v0.1 | 46.7B | 32K | apache-2.0 |
| mistralai | Timestral-209M | 209M | — | other |
| mistralai | Voxtral-Mini-3B-2507 | 4.7B | 128K | apache-2.0 |
| mistralai | Voxtral-Mini-4B-Realtime-2602 | 4.4B | 1K | apache-2.0 |
| moonshotai | Kimi-Audio-7B-Instruct | 9.8B | 8K | mit |
| moonshotai | Kimi-K2-Base | 1.03T | 128K | other |
| moonshotai | Kimi-K2-Instruct | 1.03T | 128K | other |
| moonshotai | Kimi-K2-Instruct-0905 | 1.03T | 256K | other |
| moonshotai | Kimi-K2-Thinking | 1.03T | 256K | other |
| moonshotai | Kimi-K2.5 | 1.03T | 256K | other |
| moonshotai | Kimi-K2.6 | 1.03T | 256K | other |
| moonshotai | Kimi-K2.7-Code | 1.03T | 256K | other |
| moonshotai | Kimi-K3 | 2.78T | 1M | other |
| moonshotai | Kimi-Linear-48B-A3B-Base | 49.1B | — | mit |
| moonshotai | Kimi-Linear-48B-A3B-Instruct | 49.1B | — | mit |
| moonshotai | Kimi-VL-A3B-Instruct | 16.4B | 128K | mit |
| moonshotai | Kimi-VL-A3B-Thinking | 16.4B | 128K | mit |
| moonshotai | Moonlight-16B-A3B | 16.0B | 8K | mit |
| moonshotai | Moonlight-16B-A3B-Instruct | 16.0B | 8K | mit |
| nerkyor | Qwen3.8-27B-Coder390-EfficientThink-Opus5.5-GPT6Astra-Grok4.7-DSV4Pro-K3-SFT-RLOO-MTP-DFlash2 | — | — | apache-2.0 |
| nomic-ai | nomic-embed-text-v1.5 | 137M | 2K | apache-2.0 |
| nvidia | bigvgan_v2_22khz_80band_256x | — | — | mit |
| nvidia | bigvgan_v2_44khz_128band_512x | — | — | mit |
| nvidia | Cosmos3-Edge | 3.9B | 128K | other |
| nvidia | dragon-multiturn-context-encoder | — | 512 | other |
| nvidia | dragon-multiturn-query-encoder | — | 512 | other |
| nvidia | GLM-5.3-Flash-FP4-Local | 175.2B | 1M | other |
| nvidia | Kumo-Tabular | — | — | openmdw-1.1 |
| nvidia | llama-nemotron-rerank-1b-v2 | 1.2B | 128K | other |
| nvidia | Nemotron-3-Diarization | 99M | 5K | openmdw-1.1 |
| nvidia | nemotron-3.5-asr-streaming-0.6b | 638M | 5K | other |
| nvidia | NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 | 31.6B | 256K | other |
| nvidia | NVIDIA-Nemotron-3-Nano-4B-BF16 | 4.0B | 256K | other |
| nvidia | NVIDIA-Nemotron-3-Super-120B-A12B-BF16 | 123.6B | 256K | other |
| nvidia | NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 | 560.5B | 256K | other |
| nvidia | NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB | 22.4B | 256K | other |
| nvidia | NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16 | 124.5B | 1M | other |
| nvidia | NVIDIA-Nemotron-Labs-Dory1.0-4B-BF16 | 4.0B | 256K | other |
| nvidia | PixelUMM | — | — | other |
| nvidia | Qwen3.8-Flash-Next-FP4-Local | 96.5B | 256K | other |
| openai | clip-vit-base-patch16 | — | 77 | — |
| openai | clip-vit-base-patch32 | — | 77 | — |
| openai | clip-vit-large-patch14 | 428M | 77 | — |
| openai | clip-vit-large-patch14-336 | — | 77 | — |
| openai | gpt-oss-120b | 116.8B | 128K | apache-2.0 |
| openai | gpt-oss-20b | 20.9B | 128K | apache-2.0 |
| openai | privacy-filter | 1.4B | 128K | apache-2.0 |
| openai | whisper-base | 73M | — | apache-2.0 |
| openai | whisper-large-v3 | 1.5B | — | apache-2.0 |
| openai | whisper-large-v3-turbo | 809M | — | mit |
| openai | whisper-medium | 764M | — | apache-2.0 |
| openai | whisper-small | 242M | — | apache-2.0 |
| openai | whisper-tiny | 38M | — | apache-2.0 |
| openai-community | gpt2 | 137M | — | mit |
| openbmb | MiniCPM-o-2_6 | 8.7B | 32K | apache-2.0 |
| openbmb | MiniCPM-o-4_5 | 9.4B | 40K | apache-2.0 |
| openbmb | MiniCPM-V-4_5 | 8.7B | 40K | apache-2.0 |
| openbmb | MiniCPM-V-4.6 | 1.3B | 256K | apache-2.0 |
| openbmb | MiniCPM-V-4.6-Thinking | 1.3B | 256K | apache-2.0 |
| openbmb | MiniCPM-V-4.7-1B | 1.6B | 256K | apache-2.0 |
| openbmb | MiniCPM-V-4.7-35B-A3B | 35.2B | 256K | apache-2.0 |
| openbmb | MiniCPM5-1B | 1.1B | 128K | apache-2.0 |
| openbmb | MiniCPM5-2B | 2.5B | 128K | apache-2.0 |
| openbmb | MiniCPM5-2B-DSpark | 324M | 128K | apache-2.0 |
| openbmb | VoxCPM2 | 2.3B | 32K | apache-2.0 |
| prithivMLmods | Gender-Classifier-Mini | 93M | 64 | apache-2.0 |
| ProsusAI | finbert | 109M | 512 | cc-by-nc-sa-4.0 |
| PrunaAI | Pruna-Qwen-Image-2.1 | — | — | other |
| pyannote | segmentation-3.0 | — | — | mit |
| pyannote | speaker-diarization-3.1 | — | — | mit |
| pyannote | speaker-diarization-community-1 | — | — | cc-by-4.0 |
| pyannote | wespeaker-voxceleb-resnet34-LM | — | — | cc-by-4.0 |
| Qwen | Qwen-Image-2.1 | 7.1B | — | other |
| Qwen | Qwen-Image-2.1-Turbo | 7.1B | — | other |
| Qwen | Qwen2.5-0.5B-Instruct | 494M | 32K | apache-2.0 |
| Qwen | Qwen2.5-1.5B-Instruct | 1.5B | 32K | apache-2.0 |
| Qwen | Qwen2.5-3B-Instruct | 3.1B | 32K | other |
| Qwen | Qwen2.5-7B-Instruct | 7.6B | 32K | apache-2.0 |
| Qwen | Qwen2.5-VL-7B-Instruct | 8.3B | 125K | apache-2.0 |
| Qwen | Qwen3-0.6B | 752M | 40K | apache-2.0 |
| Qwen | Qwen3-1.7B | 2.0B | 40K | apache-2.0 |
| Qwen | Qwen3-14B | 14.8B | 40K | apache-2.0 |
| Qwen | Qwen3-32B | 32.8B | 40K | apache-2.0 |
| Qwen | Qwen3-4B | 4.0B | 40K | apache-2.0 |
| Qwen | Qwen3-8B | 8.2B | 40K | apache-2.0 |
| Qwen | Qwen3-Embedding-0.6B | 596M | 32K | apache-2.0 |
| Qwen | Qwen3-TTS-12Hz-1.7B-CustomVoice | 1.9B | 32K | apache-2.0 |
| Qwen | Qwen3-VL-8B-Instruct | 8.8B | 256K | apache-2.0 |
| Qwen | Qwen3.5-2B | 2.3B | 256K | apache-2.0 |
| Qwen | Qwen3.5-4B | 4.7B | 256K | apache-2.0 |
| Qwen | Qwen3.5-9B | 9.7B | 256K | apache-2.0 |
| Qwen | Qwen3.8-27B | 27.8B | 256K | apache-2.0 |
| Qwen | Qwen3.8-Flash-Next | 180.0B | 256K | other |
| RadixArk | Kimi-K3-DSpark | 2.2B | 1M | — |
| SamLowe | roberta-base-go_emotions | 125M | 514 | mit |
| sentence-transformers | all-MiniLM-L6-v2 | 23M | 512 | apache-2.0 |
| sentence-transformers | all-mpnet-base-v2 | 109M | 514 | apache-2.0 |
| sentence-transformers | paraphrase-multilingual-MiniLM-L12-v2 | 118M | 512 | apache-2.0 |
| sentence-transformers | paraphrase-multilingual-mpnet-base-v2 | 278M | 514 | apache-2.0 |
| stabilityai | sd-turbo | 866M | — | — |
| stabilityai | sd-vae-ft-mse | 84M | — | mit |
| stabilityai | sdxl-turbo | 2.6B | — | other |
| stabilityai | sdxl-vae | 84M | — | mit |
| stabilityai | stable-audio-3-medium | 2.3B | — | other |
| stabilityai | stable-diffusion-3-medium-diffusers | 2.1B | — | other |
| stabilityai | stable-diffusion-3.5-large | 8.1B | — | other |
| stabilityai | stable-diffusion-3.5-medium | 2.5B | — | other |
| stabilityai | stable-diffusion-xl-base-1.0 | 2.6B | — | openrail++ |
| stabilityai | stable-diffusion-xl-refiner-1.0 | 2.3B | — | openrail++ |
| stabilityai | stable-fast-3d | 1.0B | — | other |
| stabilityai | stable-video-diffusion-img2vid | 1.5B | — | other |
| stabilityai | stable-video-diffusion-img2vid-xt | 1.5B | — | other |
| stabilityai | TripoSR | — | — | mit |
| SulphurAI | Sulphur-2-base | — | — | — |
| Systran | faster-whisper-small | — | — | mit |
| tencent | AuK | — | — | mit |
| tencent | Hunyuan-7B-Instruct | 7.5B | 32K | — |
| tencent | Hunyuan-A13B-Instruct | 80.4B | 32K | other |
| tencent | Hunyuan3D-2 | — | — | other |
| tencent | Hunyuan3D-2.1 | — | — | other |
| tencent | Hunyuan3D-2mini | — | — | other |
| tencent | HunyuanImage-3.0-Instruct | 83.0B | 22K | other |
| tencent | HunyuanOCR | 1.1B | 128K | other |
| tencent | Hy-Memory-30B-A3B | 30.1B | 256K | apache-2.0 |
| tencent | Hy-MT2-1.8B | 2.0B | 256K | apache-2.0 |
| tencent | Hy3 | 298.8B | 256K | apache-2.0 |
| tencent | Hy3-preview | 298.8B | 256K | other |
| tencent | Youtu-Parsing-Omni | 5.3B | 1M | other |
| tiiuae | falcon-7b | 7.2B | — | apache-2.0 |
| tiiuae | falcon-7b-instruct | 7.2B | — | apache-2.0 |
| tiiuae | Falcon-H1-0.5B-Base | 521M | 16K | other |
| tiiuae | Falcon-H1-1.5B-Base | 1.6B | 128K | other |
| tiiuae | Falcon-H1-1.5B-Deep-Instruct | 1.6B | 128K | other |
| tiiuae | Falcon-H1-3B-Instruct | 3.1B | 128K | other |
| tiiuae | Falcon-H1-7B-Instruct | 7.6B | 256K | other |
| tiiuae | falcon-mamba-7b | 7.3B | — | other |
| tiiuae | falcon-mamba-7b-instruct | 7.3B | — | other |
| tiiuae | falcon-mamba-tiny-dev | 9M | — | — |
| tiiuae | Falcon-Perception | 632M | — | apache-2.0 |
| tiiuae | Falcon3-10B-Instruct | 10.3B | 32K | other |
| tiiuae | Falcon3-1B-Instruct | 1.7B | 8K | other |
| tiiuae | Falcon3-3B-Instruct | 3.2B | 32K | other |
| tiiuae | Falcon3-7B-Instruct | 7.5B | 32K | other |
| timm | mobilenetv3_small_100.lamb_in1k | 3M | — | apache-2.0 |
| trl-internal-testing | tiny-Qwen2ForCausalLM-2.5 | 2M | 32K | — |
| Viggle | Qwen-Image-2.1-viggle-turbo | 7.1B | — | other |
| WarmBloodAban | Minimax-h3_Singularity | — | — | apache-2.0 |
| xai-org | grok-1 | — | — | apache-2.0 |
| xai-org | grok-2 | — | 128K | — |
| Xenova | all-MiniLM-L6-v2 | — | 512 | apache-2.0 |
| XiaomiMiMo | MiMo-V2.6-Flash-RL | 310.8B | 1M | mit |
| XiaomiMiMo | MiMo-V2.6-Pro-RL | 1.02T | 1M | mit |
| XingChen-AGI | Xing4.0-29B-A4B | 31.2B | 256K | apache-2.0 |
| zai-org | chatglm2-6b | — | — | — |
| zai-org | glm-4-9b-chat | 9.4B | — | other |
| zai-org | GLM-4.1V-9B-Thinking | 10.3B | 64K | mit |
| zai-org | GLM-4.5 | 358.3B | 128K | mit |
| zai-org | GLM-4.5-Air | 110.5B | 128K | mit |
| zai-org | GLM-4.7 | 358.3B | 198K | mit |
| zai-org | GLM-4.7-Flash | 31.2B | 198K | mit |
| zai-org | GLM-5 | 753.9B | 198K | mit |
| zai-org | GLM-5.1 | 753.9B | 198K | mit |
| zai-org | GLM-5.2 | 753.3B | 1M | mit |
| zai-org | GLM-5.3 | 753.3B | 1M | other |
| zai-org | GLM-5.3-Flash | 321.3B | 1M | mit |
| zai-org | GLM-5.3-Flash-BF16 | 321.3B | 1M | mit |
| zai-org | GLM-OCR | 1.3B | 128K | mit |
Cite this dataset
The register is published under CC BY 4.0. Attribution to The Neural Net.
APA
The Neural Net. (2026). The Neural Net model register [Data set]. https://theneuralnet.com/models
BibTeX
@misc{theneuralnet_model_register,
title = {The Neural Net model register},
author = {{The Neural Net}},
year = {2026},
url = {https://theneuralnet.com/models},
note = {CC BY 4.0}
}HTML
<a href="https://theneuralnet.com/models">The Neural Net model register</a>