{"slug":"exllamav3","name":"exllamav3","category":"local-inference","categoryName":"Local inference & serving","audience":["ai-era"],"primary":"ai-era","openClosed":"open","pricing":"open-source","license":"MIT","maintained":"yes","officialUrl":"https://github.com/turboderp-org/exllamav3","repo":"https://github.com/turboderp-org/exllamav3","latestVersion":"v1.6.0","latestRelease":"2026-10-08","stars":1723,"starsAsOf":"2026-10-22","description":"An optimized quantization and inference library for running LLMs locally on modern consumer-class GPUs ","descriptionZh":"ExLlama 第三版","callMethods":["SDK"],"platforms":[],"addedAt":"2026-10-10","updatedAt":"2026-10-22","topics":[],"language":"Python","lastPush":"2026-10-20","formerly":null,"packages":[{"registry":"pypi","name":"exllamav3","url":"https://pypi.org/project/exllamav3/","versionsUrl":"https://pypi.org/project/exllamav3/#history","latestVersion":"1.6.0","latestDate":"2026-10-09"}],"recentVersions":[{"version":"v1.6.0","date":"2026-10-08","prerelease":false,"url":"https://github.com/turboderp-org/exllamav3/releases/tag/v1.6.0","source":"GitHub Release"},{"version":"v1.5.4","date":"2026-10-03","prerelease":false,"url":"https://github.com/turboderp-org/exllamav3/releases/tag/v1.5.4","source":"GitHub Release"},{"version":"v1.5.3","date":"2026-09-27","prerelease":false,"url":"https://github.com/turboderp-org/exllamav3/releases/tag/v1.5.3","source":"GitHub Release"},{"version":"v1.5.2","date":"2026-09-26","prerelease":false,"url":"https://github.com/turboderp-org/exllamav3/releases/tag/v1.5.2","source":"GitHub Release"},{"version":"v1.5.1","date":"2026-09-20","prerelease":false,"url":"https://github.com/turboderp-org/exllamav3/releases/tag/v1.5.1","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：ExLlama 第三版","sources":["oss","github-pool"],"record":"https://aimap.page/api/v1/software/exllamav3.json","pages":{"en":"https://aimap.page/en/software/exllamav3/","zh-hans":"https://aimap.page/zh-hans/software/exllamav3/"}}