Models & Labs
MiniCPM5-2B targets sub-agent roles with high efficiency
Sam Witteveenhigh confidence
Why it matters
- →MiniCPM5-2B demonstrates that specialized training can make small models competitive with larger ones in agent workflows.
- →The use of JustRL II offers a new training recipe for optimizing LLMs for autonomous decision-making.
- →Developers gain a lightweight, cost-effective option for deploying high-frequency sub-agent tasks.
OpenBMB has released MiniCPM5-2B, a 2-billion-parameter model designed specifically for autonomous agent sub-tasks. The release highlights the use of JustRL II training techniques to enhance performance in tool-use and reasoning benchmarks compared to larger alternatives. Hosted on Hugging Face and GitHub, the model is positioned as an efficient solution for building multi-step automation systems where latency and cost are critical constraints.
Read originalMore from Sam Witteveen
More in Models & Labs
Models & Labscoding
llama.cpp b10996 adds CUDA 13 and ROCm 10.0 builds
This release quietly closes the hardware gap for local inference by adding native support for CUDA 13 and ROCm 10.0 across Linux and Windows. NVIDIA users can now leverage newer driver stacks without waiting for upstream updates, while AMD GPU owners finally get first-class ROCm 10 binaries that match the maturity of their CUDA counterparts. Apple Silicon builds remain available but KleidiAI is explicitly disabled here, suggesting a focus on stability over new kernel optimizations for this specific iteration. The inclusion of openEuler support for Huawei's Ascend chips further broadens the ecosystem beyond standard x86 and ARM consumer hardware.
llama.cpp Releases
Models & Labsmodels
Llama.cpp b10981 release enhances OpenVINO support
The latest b10981 release of llama.cpp brings significant improvements to OpenVINO integration, particularly in optimizing stateful decode and GPU MoE inference. By addressing issues like stateful decode errors and enhancing the handling of sliding-window layers, this update ensures more reliable and efficient model performance. The release also introduces new features such as the GGML_OPENVINO_REQUANT_KQUANT for 4-bit requantization and improved handling of multi-head models. These changes make llama.cpp more robust and versatile, especially for developers working with complex AI models on diverse hardware setups.