Models & Labs
Moonshot releases Kimi K3 with 2.8 trillion parameters
Fireshipmedium confidence
Why it matters
- →Kimi K3's 2.8 trillion parameters represent a new scale in AI model size.
- →The model's open-weight nature could foster innovation and experimentation.
- →Its performance will influence future AI development and applications.
Moonshot has launched Kimi K3, an AI model with a staggering 2.8 trillion parameters, setting a new benchmark in the scale of open-weight AI models. This release could significantly enhance the model's ability to process complex data, although its practical performance remains to be seen. The introduction of Kimi K3 highlights the ongoing trend of increasing AI model sizes, which may lead to more sophisticated AI applications. The effectiveness of Kimi K3 will ultimately depend on its real-world application and performance.
Read originalMore from Fireship
More in Models & Labs
Models & Labsmodels
llama.cpp b10083 Release Expands Platform Support
The latest b10083 release of llama.cpp continues its trend of broadening platform compatibility, making it a versatile choice for developers across different systems. Notably, this update includes support for Ubuntu with ROCm 7.2, enhancing performance for AMD GPU users. Windows users benefit from updated CUDA support, with DLLs for both CUDA 12.4 and 13.3, ensuring compatibility with the latest NVIDIA technologies. While no groundbreaking new features are introduced, the release solidifies llama.cpp's position as a flexible inference runtime across diverse hardware setups.
llama.cpp Releases
Models & Labsmodels
llama.cpp b10085 release updates Qwen3-VL interpolation
The latest b10085 release of llama.cpp addresses a key issue with the Qwen3-VL vision model's position embedding interpolation. By aligning the interpolation method with the transformers reference, the update ensures more accurate grounding coordinates, particularly for larger and non-square images. This change is crucial for developers working with image processing tasks, as it reduces discrepancies in image scaling. While the update doesn't introduce new models, it enhances the precision of existing functionalities, making llama.cpp a more reliable tool for AI developers.
llama.cpp Releases
Models & Labsmodels
Llama.cpp b10089 Release Enhances CUDA Support
The latest b10089 release of llama.cpp significantly enhances CUDA support by adding k-quant and i-quant capabilities to the GET_ROWS function. This update allows for more efficient device-side embedding lookups, reducing the need to fallback to the host and improving performance for single-device graphs. By factoring out super-block dequantizers into shared device functions, the release ensures that all quantized GGML types can now take the direct device path. This marks a notable improvement in CUDA's handling of quantized data, making it more robust and efficient.
llama.cpp Releases