{"slug":"exllamav2","name":"exllamav2","category":"local-inference","categoryName":"Local inference & serving","audience":["ai-era"],"primary":"ai-era","openClosed":"open","pricing":"open-source","license":"MIT","maintained":"stale","officialUrl":"https://github.com/turboderp-org/exllamav2","repo":"https://github.com/turboderp-org/exllamav2","latestVersion":"v0.3.2","latestRelease":"2025-07-13","stars":4631,"starsAsOf":"2026-10-04","description":"A fast inference library for running LLMs locally on modern consumer-class GPUs","descriptionZh":"消费级 GPU 高速量化推理","callMethods":["SDK"],"platforms":[],"addedAt":"2026-10-10","updatedAt":"2026-10-04","topics":[],"language":"Python","lastPush":"2026-03-04","formerly":null,"packages":[],"recentVersions":[{"version":"v0.3.2","date":"2025-07-13","prerelease":false,"url":"https://github.com/turboderp-org/exllamav2/releases/tag/v0.3.2","source":"GitHub Release"},{"version":"v0.3.1","date":"2025-05-27","prerelease":false,"url":"https://github.com/turboderp-org/exllamav2/releases/tag/v0.3.1","source":"GitHub Release"},{"version":"v0.3.0","date":"2025-05-12","prerelease":false,"url":"https://github.com/turboderp-org/exllamav2/releases/tag/v0.3.0","source":"GitHub Release"},{"version":"v0.2.9","date":"2025-04-23","prerelease":false,"url":"https://github.com/turboderp-org/exllamav2/releases/tag/v0.2.9","source":"GitHub Release"},{"version":"v0.2.8","date":"2025-02-08","prerelease":false,"url":"https://github.com/turboderp-org/exllamav2/releases/tag/v0.2.8","source":"GitHub Release"}],"alternatives":["ollama","llama-cpp","vllm","cherry-studio","localai","exo","sglang","mlx"],"stacks":[],"scenarios":["switch-models","run-models-locally","use-ai-compliantly-in-china","learn-ai"],"problems":[],"reasonZh":"开源大库收录：消费级 GPU 高速量化推理","sources":["oss"],"record":"https://aimap.page/api/v1/software/exllamav2.json","pages":{"en":"https://aimap.page/en/software/exllamav2/","zh-hans":"https://aimap.page/zh-hans/software/exllamav2/"}}