Top open language models
Language models for text generation, understanding, and transformation.
How this list works: ranked by Hugging Face downloads in the last 30 days, among models with 1,000+ downloads.
| # | Model | Author | Downloads (30 days) | Likes | Size | License | Commercial use | Runs on |
|---|---|---|---|---|---|---|---|---|
| 1 | bert-base-uncased | google-bert | 30.5M | 3.4K | – | Apache 2.0 | Yes | CPU |
| 2 | Qwen3-0.6B | Qwen | 29.5M | 1.8K | 600M | Apache 2.0 | Yes | GPU |
| 3 | t5-small | google-t5 | 24.2M | 684 | – | Apache 2.0 | Yes | CPU |
| 4 | gpt2 | openai-community | 17.2M | 4.3K | – | MIT | Yes | CPU |
| 5 | bge-reranker-v2-m3 | BAAI | 15.7M | 1.3K | – | Apache 2.0 | Yes | GPU |
| 6 | Qwen3-4B | Qwen | 11.8M | 765 | 4B | Apache 2.0 | Yes | GPU |
| 7 | xlm-roberta-base | FacebookAI | 9.4M | 959 | – | MIT | Yes | CPU |
| 8 | Qwen3-8B | Qwen | 8.9M | 2.1K | 8B | Apache 2.0 | Yes | GPU |
| 9 | Qwen3-14B | Qwen | 8.4M | 510 | 14B | Apache 2.0 | Yes | GPU |
| 10 | roberta-base | FacebookAI | 7.6M | 691 | – | MIT | Yes | GPU |
| 11 | distilbert-base-uncased | distilbert | 7.2M | 1.5K | – | Apache 2.0 | Yes | GPU |
| 12 | Qwen2.5-7B-Instruct | Qwen | 6.8M | 2.4K | 7B | Apache 2.0 | Yes | GPU |
| 13 | roberta-large | FacebookAI | 6.5M | 335 | – | MIT | Yes | CPU |
| 14 | gpt-oss-20b | openai | 5.9M | 5.2K | 20B | Apache 2.0 | Yes | GPU |
| 15 | opt-125m | 5.8M | 330 | 125M | Custom (other) | Check the license | GPU | |
| 16 | Qwen2.5-0.5B-Instruct | Qwen | 5.8M | 700 | 500M | Apache 2.0 | Yes | GPU |
| 17 | mdeberta-v3-base | microsoft | 5.7M | 258 | – | MIT | Yes | GPU |
| 18 | Qwen2.5-1.5B-Instruct | Qwen | 5.6M | 893 | 1.5B | Apache 2.0 | Yes | GPU |
| 19 | Llama-3.1-8B-Instruct | meta-llama | 5.5M | 8.5K | 8B | Llama 3.1 license | Yes, with conditions | GPU |
| 20 | DeepSeek-V3.2 | deepseek-ai | 5.3M | 1.6K | – | MIT | Yes | GPU |
| 21 | Llama-3.2-1B-Instruct | meta-llama | 5.1M | 1.9K | 1B | Llama 3.2 license | Yes, with conditions | GPU |
| 22 | Ornith-1.5-9B-GGUF | ornith-ai | 4.9M | 563 | 9B | MIT | Yes | CPU |
| 23 | esm2_t33_650M_UR50D | 4.9M | 103 | – | MIT | Yes | GPU | |
| 24 | dolphin-2.9.1-yi-1.5-34b | dphn | 4.7M | 83 | 34B | Apache 2.0 | Yes | GPU |
| 25 | roberta-base-go_emotions | SamLowe | 4.6M | 706 | – | MIT | Yes | GPU |
Other model comparisons
Top open image modelsTop open audio modelsTop open video modelsTop open embedding modelsTop open multimodal modelsTop open text-generation models (LLMs)Top open text-to-image modelsTop open text-to-speech modelsTop open speech-recognition modelsTop open feature-extraction modelsTop open sentence-similarity modelsTop open image-to-text modelsTop open vision-language modelsTop open image-classification modelsTop open image-segmentation modelsTop open object-detection modelsTop open depth-estimation modelsTop open audio-classification modelsTop open video-classification models