Loading
Loading
Open weights
Counts come from the public Hugging Face Hub API and the public GitHub API. A row appears only when that request returned a number.
Live
Public Hugging Face models API. huggingface.co/models.
| Model | Downloads | Pipeline |
|---|---|---|
| sentence-transformers/all-MiniLM-L6-v2 | 191.7M | sentence-similarity |
| cross-encoder/ms-marco-MiniLM-L6-v2 | 71.1M | text-ranking |
| BAAI/bge-small-en-v1.5 | 53.6M | feature-extraction |
| sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 | 39.8M | sentence-similarity |
| google/electra-base-discriminator | 33.2M | — |
| BAAI/bge-m3 | 29.7M | sentence-similarity |
| google-bert/bert-base-uncased | 29M | fill-mask |
| Comfy-Org/MiniMax-H3 | 26.5M | — |
Public Hugging Face models API. huggingface.co/models.
| Model | Likes | Pipeline |
|---|---|---|
| Qwen/Qwen3.8-27B | 18.4K | image-text-to-text |
| black-forest-labs/FLUX.1-dev | 15.8K | text-to-image |
| deepseek-ai/DeepSeek-R1 | 14.4K | text-generation |
| moonshotai/Kimi-K3 | 11.8K | image-text-to-text |
| Lightricks/LTX-2.5 | 9.3K | image-to-video |
| meta-llama/Llama-3.1-8B-Instruct | 8.6K | text-generation |
| stabilityai/stable-diffusion-xl-base-1.0 | 8.4K | text-to-image |
| hexgrad/Kokoro-82M | 7.3K | text-to-speech |
Public Hugging Face models API. huggingface.co/models.
| Model | Downloads | Pipeline |
|---|---|---|
| deepseek-ai/DeepSeek-V4.1-Flash-1017 | 85.3K | image-text-to-text |
| RecursiveSI/flint | 6.4K | text-generation |
| black-forest-labs/flux-3-image-klein-comfy | 660.9K | image-to-image |
| XHToken/Spark-X2.6-4B | 3.5K | text-generation |
| Lightricks/LTX-2.5 | 2.1M | image-to-video |
| Nanbeige/Nanbeige4.3-33B | 0 | text-generation |
| MiniMaxAI/MiniMax-M3.1-Flash | 7.4K | image-text-to-text |
| OpenMOSS-Team/MOSS-Image-SFT | 10.8K | text-to-image |
Star count and the latest release tag from the GitHub API. GitHub API.
| Repository | Stars | Latest release |
|---|---|---|
| ggml-org/llama.cpp LLM inference in C/C++ | 132.4K | b11889 |
| huggingface/transformers 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference a | 168.2K | v5.20.2 |
| vllm-project/vllm A high-throughput and memory-efficient inference and serving engine for LLMs | 95.5K | v0.32.0 |
| ollama/ollama Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models. | 184.8K | v0.40.11 |
| open-webui/open-webui User-friendly AI Interface (Supports Ollama, OpenAI API, ...) | 156.8K | v0.12.4 |
| langchain-ai/langchain The agent engineering platform. | 148.5K | langchain-core==1.7.0 |
| comfyanonymous/ComfyUI The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world. | 143K | v0.42.1 |
| ggml-org/whisper.cpp Port of OpenAI's Whisper model in C/C++ | 54.7K | v1.9.5 |
| continuedev/continue open-source coding agent | 36.3K | v2.1.0-vscode |
| AUTOMATIC1111/stable-diffusion-webui Stable Diffusion web UI | 165.1K | v1.10.1 |