サイト内検索

AI モデル 84757

• gemma-4-E4B-it-MLX-4bit↗

  lmstudio-community

  _👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord_. **Model creator**: google **Original model**: gemma-4-E4B-it **MLX quantization**: provided by LM Studio team using mlx_vlm 4-bit quantized version of gemma-4-E4B-it using MLX, optimized for Apple Silicon.

• Qwen3.5-9B-Q5_K_M.gguf↗

  Manojb

• ANIMA-Phi-Neptune-Mistral-7B-Mistral-7B-Instruct-v0.1-GGUF↗

  MaziyarPanahi

• Ayla-Light-12B-Stock-GGUF↗

  MaziyarPanahi

• LongCat-Flash-Chat↗

  meituan-longcat

  We introduce LongCat-Flash, a powerful and efficient language model with 560 billion total parameters, featuring an innovative Mixture-of-Experts (MoE) architecture. The model incorporates a dynamic computation mechanism that activates 18.6B∼31.3B parameters (averaging∼27B) based on contextual demands, optimizing both computational efficiency and performance. To achieve advanced training and inference efficiency, we employ a shortcut-connected architecture that expands computation-communication overlap window, achieving over 100 tokens per second (TPS) for inference cost-effectively. Our comprehensive training and scaling strategies ensure stable, efficient training, while tailored data strategies enhance model performance. Now we release LongCat-Flash-Chat, a non-thinking foundation model that delivers highly competitive performance among leading models, with exceptional strengths in agentic tasks. LongCat-Flash is designed and optimized under two key principles: efficient computation utilization, as well as efficient training and inference. Specifically, (1) As not all tokens are equal, we introduce the zero-computation experts mechanism in MoE blocks to allocate a dynamic computation budget to important tokens based on their significance, i.e., activating 18.6 to 31.3 billion parameters (out of 560 billion total) based on contextual demands. To ensure consistent computation load, we employ expert bias adjusted by a PID-controller, maintaining an average of∼27 billion activated parameters per token. (2) As communication overhead becomes a bottleneck during MoE model scaling, we incorporate the Shortcut-connected MoE (ScMoE) design to expand the computation-communication overlap window. Combined with customized infrastructure optimizations, this design enables training at a massive scale of over tens of thousands accelerators and inference with high throughput and low latency.

• Lucy-128k-gguf↗

  Menlo

• d186↗

  Mhair

• NextCoder-32B↗

  Microsoft

• tapex-large↗

  Microsoft

• tinymixtral-v2.0-beta↗

  mikecovlee