{"name":"ggml","repo":"ggml-org/ggml","url":"https://midorreal.com/project/ggml-org-ggml","repository":"https://github.com/ggml-org/ggml","description":"Tensor library for machine learning","facts":{"license":{"value":"MIT","source":"https://github.com/ggml-org/ggml","checked":"22 Nov 2026"},"language":{"value":"C++","source":"https://github.com/ggml-org/ggml","checked":"22 Nov 2026"},"homepage":{"value":"https://github.com/ggml-org","source":"https://github.com/ggml-org","checked":"22 Nov 2026"},"last_release":{"value":"v1.0.0, 13 Nov 2026","source":"https://github.com/ggml-org/ggml/releases","checked":"22 Nov 2026"},"releases":{"value":"45","source":"https://github.com/ggml-org/ggml/releases","checked":"19 Nov 2026"},"contributors":{"value":"919","source":"https://github.com/ggml-org/ggml/graphs/contributors","checked":"19 Nov 2026"},"archived":{"value":"no","source":"https://github.com/ggml-org/ggml","checked":"22 Nov 2026"}},"stars":16149.0,"writeup":{"what_it_is":"ggml is a tensor library for machine learning, written in plain C/C++ with no dependencies. Its stated goal is to be a simple, portable and efficient tensor library with minimal setup.","audience":"Developers building machine learning software who want a lightweight C/C++ tensor library","claims":[{"kind":"specific","claim":"Implemented in plain C/C++ without any dependencies","excerpt":"Plain C/C++ implementation without any dependencies","status":"not_checked"},{"kind":"specific","claim":"Runs on multiple CPU architectures and WebAssembly","excerpt":"Cross-platform - x86, ARM, RISC-V, LoongArch, PowerPC, s390x, and WebAssembly","status":"not_checked"},{"kind":"specific","claim":"Includes SIMD-optimized kernels for x86, ARM and RISC-V","excerpt":"SIMD-optimized kernels for x86, ARM, and RISC-V","status":"not_checked"},{"kind":"specific","claim":"Supports CPU, GPU, NPU and browser backends","excerpt":"Broad backend support - CPU, GPU, NPU, and browser","status":"not_checked"},{"kind":"specific","claim":"Supports 2- to 8-bit integer quantization and MXFP4 and NVFP4 formats","excerpt":"2- to 8-bit integer quantization, plus MXFP4 and NVFP4 microscaling formats","status":"not_checked"}],"alternatives":[],"written_by":"AI, from the project's README","date":"2026-11-14"},"why_now":null,"owner_supplied":null,"score":{"verdict":"overhyped","hype":97,"reality":62,"gap":35,"momentum":null,"confidence":85,"version":"score-2.0","rule":"verdict-2.0","calculated_at":"2026-11-22T07:00:00+00:00","verdict_source":"rule"},"early_read":null,"changes":[{"date":"2026-11-13T08:34:21+00:00","text":"Latest release v1.0.0","source":"https://github.com/ggml-org/ggml/releases"},{"date":"2025-09-20T13:54:38+00:00","text":"First release","source":"https://github.com/ggml-org/ggml/releases"},{"date":"2022-09-18T17:07:19+00:00","text":"Repository created","source":"https://github.com/ggml-org/ggml"}],"cite":"ggml is a GitHub project at https://github.com/ggml-org/ggml written mainly in C++, described there as \"Tensor library for machine learning\".","attribution":"Data from Mid or Real, https://midorreal.com/project/ggml-org-ggml, checked 22 November 2026. Attribution with a link is required.","still_real":null}