Product
5 Interestana reports mention llama.cpp, newest first. Each is summarised from the original reporting and links back to its publisher.
Underdog, a division of Conway Research, has released Saluki 27B, a highly compressed 2-bit GGUF model derived from Qwen3.8-27B, under the permissive Apache 2.0 license. This new model is specifically engineered for on-device AI assistants and achieves a remarkable file…
The Hugging Face Transformers library has integrated support for quantization methods developed by the llama.cpp project. This integration allows users to load and run large language models (LLMs) that have been quantized using llama.cpp's techniques directly within the Transformers ecosystem.
A new guide released on September 18, 2026, ranks eleven open-source agent harnesses designed to work with local Large Language Models (LLMs). An agent harness is defined as the software that runs tools, manages the model's state, handles permissions…
Mistral AI has released Shieldstral 1.0 3B, an open-weights, policy-adaptive multimodal safety classifier designed to handle content moderation by framing it as a single yes/no question rather than relying on a predefined taxonomy of harm categories.
A tutorial has been published detailing the deployment of the 1-bit Bonsai-27B language model, a significant advancement in efficient AI model execution. The deployment leverages a specialized fork of llama.cpp developed by PrismML, which incorporates essential CUDA kernels.