models
Open weights, fine-tunes and adapters. Every listing here comes live from the Hugging Face Hub, attributed to it, and links back to the source.
Nemotron-3-Embed-1B-BF16Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16Nemotron-3-Embed-8B-BF16nomicai-modernbert-embed-base-bf16acestep-v15-xl-turbo-bf16bge-small-en-v1.5-bf16all-MiniLM-L6-v2-bf16DeepSeek-OCR-2-bf16embeddinggemma-300m-bf16Argus-Colqwen3.5-4b-v0-bf16Argus-Colqwen3.5-2b-v0-bf16Argus-Colqwen3.5-9b-v0-bf16Nemotron-3-Embed-1B-BF16-8bitSapBERT-from-PubMedBERT-fulltext_bf16Nemotron-3-Embed-1B-BF16-4bitQwen3-VL-Embedding-2B-bf16LFM2.5-Embedding-350M-bf16Qwen3-Embedding-8B-MLX-BF16Kimi-VL-A3B-Thinking-2506-bf16Nemotron-3-Embed-1B-BF16Qwen3-Embedding-0.6B-mlx-bf16embeddinggemma-300m-qat-q8_0-unquantized-bf16DeepSeek-OCR-bf16SapBERT-UMLS-2020AB-all-lang-from-XLMR-ST_bf16DeepSeek-OCR-Latest-BF16.I64snowflake-arctic-embed-l-v2.0-bf16embeddinggemma-300m-qat-q4_0-unquantized-bf16Nemotron-3-Nano-Omni-AEON-Ultimate-Uncensored-BF16InternVL3-8B-bf16InternVL3-14B-bf16
