Search: “local-ai”

Build **b8779** is an incremental release of [llama.cpp](https://github.com/ggml-org/llama.cpp), an open-source C/C++ framework for running large language model inference locally and in the cloud. Lik

llama.cpp build b8781 is the latest release of the open-source C/C++ LLM inference framework, published on April 13, 2026. Its primary change introduces a dedicated DeepSeek v3.2 chat parser along wit

Ollama v0.20.7 is a patch-level release in the v0.20.x series of Ollama, the open-source platform for running large language models locally. Based on the progression of the 0.20.x releases — which hav

Ollama v0.20.7-rc0 is a release candidate that introduces renderer tests for the `nothink` mode specific to the Gemma 4 model (PR #15554). The `nothink` feature allows Gemma 4 to bypass its default ch

Ollama v0.20.8-rc0 is a release candidate that introduces MLX support for Google's Gemma 4 model family on Apple Silicon, addressing a prior limitation where Ollama would throw a `Gemma4ForConditional

Build b8766 is a numbered incremental release of llama.cpp, the open-source C/C++ framework for running large language model inference locally. Like other builds in its rapid release cycle, it likely

Build **b8769** is an incremental release of [llama.cpp](https://github.com/ggml-org/llama.cpp), the open-source C/C++ library for running large language model inference locally. Like all llama.cpp bu

**b8770** is a sequentially numbered automated build release of [llama.cpp](https://github.com/ggml-org/llama.cpp), an open-source C/C++ framework for running large language model (LLM) inference loca

Ollama v0.20.6-rc1 is a pre-release candidate for the v0.20.6 update to Ollama, the open-source framework for running large language models locally. Based on the associated v0.20.6 pre-release notes,

**b8757** is a versioned build release of [llama.cpp](https://github.com/ggml-org/llama.cpp), an open-source C/C++ framework for running large language model (LLM) inference locally on consumer hardwa

Build **b8759** is an incremental release of [llama.cpp](https://github.com/ggml-org/llama.cpp), the open-source C/C++ library for local LLM inference using GGUF-format models. Like other builds in th

llama.cpp release **b8760** is a build of the open-source C/C++ LLM inference framework, with its primary change being a tensor parallelism (TP) fix for Qwen 3 regarding next data split (PR #21732). P

Build b8761 is an incremental release of **llama.cpp**, an open-source C/C++ framework for running large language model (LLM) inference locally with minimal dependencies. Like neighboring builds in th

llama.cpp build **b8762**, released on April 11, 2026, is centered on the addition of MERaLiON-2 multimodal audio support to the project's `mtmd` (multimodal) framework. It adds support for A*STAR's M

llama.cpp build b8763 is a release of the open-source C/C++ LLM inference library, published on April 11, 2025, with the primary change being a CUDA optimization to skip compilation of superfluous fla