전체 검색
AI 모델 84762
- jina-bert-flash-implementation↗
jinaai
To run the model on GPU, you need to install Flash Attention. You may either install from pypi (which may not work with fused-dense), or from source. To install from source, clone the GitHub repository: The code provided here should work with commit `43950dd`. Change to the cloned repo and install: If you would like to use fused MLPs (e.g. to use activation checkpointing), you may install fused-dense also from source:
- Tiny-Chick-10M-V2↗
kurcontko
- LanguageBind_Audio_FT↗
LanguageBind
- Mistral-Small-3.2-24B-Instruct-2506-GGUF↗
lmstudio-community
*👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord*. **Model creator:** mistralai **Original model**: Mistral-Small-3.2-24B-Instruct-2506 **GGUF quantization:** provided by lmmy based on `llama.cpp` release b5726 Supports dozens of languages, including English, French, German, Spanish, Portuguese, Italian, Japanese, Korean, Russian, Chinese, Arabic, Persian, Indonesian, Malay, Nepali, Polish, Romanian, Serbian, Swedish, Turkish, Ukrainian, Vietnamese, Hindi, and Bengali.
- NVIDIA-Nemotron-3-Nano-30B-A3B-MLX-4bit↗
lmstudio-community
_👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord_. **Model creator**: nvidia **Original model**: NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 **MLX quantization**: provided by LM Studio team using mlx_lm 4-bit quantized version of NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 using MLX, optimized for Apple Silicon.
- MeinaUnreal_V3↗
Meina
- LinkBERT-base↗
michiyasunaga
- VibeVoice-Realtime-0.5B↗
Microsoft
VibeVoice-Realtime is a **lightweight real‑time** text-to-speech model supporting **streaming text input** and **robust long-form speech generation**. It can be used to build realtime TTS services, narrate live data streams, and let different LLMs start speaking from their very first tokens (plug in your preferred model) long before a full answer is generated. It produces initial audible speech in **~300 ms** (hardware dependent). Although the model is primarily built for English, we found that it still exhibits a certain level of multilingual capability—and even performs reasonably well in some languages. We provide nine additional languages (German, French, Italian, Japanese, Korean, Dutch, Polish, Portuguese, and Spanish) for users to explore and share feedback. The model uses an interleaved, windowed design: it incrementally encodes incoming text chunks while, in parallel, continuing diffusion-based acoustic latent generation from prior context. Unlike the full multi-speaker long-form variants, this streaming model removes the semantic tokenizer and relies solely on an efficient acoustic tokenizer operating at an ultra-low frame rate (7.5 Hz).
- waiMatureIllustrious_v20↗
misri
- DeepSeek-Coder-V2-Lite-Instruct-4bit-mlx↗
mlx-community
