{"id":14964830,"url":"https://github.com/shinomakoi/magi_llm_gui","last_synced_at":"2025-10-05T11:31:18.010Z","repository":{"id":153165550,"uuid":"625246380","full_name":"shinomakoi/magi_llm_gui","owner":"shinomakoi","description":"A Qt GUI for large language models","archived":false,"fork":false,"pushed_at":"2023-11-17T17:16:50.000Z","size":660,"stargazers_count":40,"open_issues_count":4,"forks_count":4,"subscribers_count":3,"default_branch":"main","last_synced_at":"2024-10-30T00:52:25.464Z","etag":null,"topics":["exllama","gui","llama","llamacpp","llm","python","qt"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/shinomakoi.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null}},"created_at":"2023-04-08T14:16:17.000Z","updated_at":"2024-06-05T17:37:38.000Z","dependencies_parsed_at":"2023-11-17T18:44:10.756Z","dependency_job_id":null,"html_url":"https://github.com/shinomakoi/magi_llm_gui","commit_stats":null,"previous_names":[],"tags_count":1,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/shinomakoi%2Fmagi_llm_gui","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/shinomakoi%2Fmagi_llm_gui/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/shinomakoi%2Fmagi_llm_gui/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/shinomakoi%2Fmagi_llm_gui/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/shinomakoi","download_url":"https://codeload.github.com/shinomakoi/magi_llm_gui/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":235208998,"owners_count":18953003,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["exllama","gui","llama","llamacpp","llm","python","qt"],"created_at":"2024-09-24T13:33:50.561Z","updated_at":"2025-10-05T11:31:12.706Z","avatar_url":"https://github.com/shinomakoi.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Magi LLM GUI\nA Qt GUI for large language models for Windows, Linux (and Mac?)\n\nUses Exllama and llama.cpp as backends.\n\n**NOTICE**\n\nThis has been replaced by https://github.com/shinomakoi/AI-Messenger\n\n**Installation:**\n\nFirst make sure Python (3.10+ recommended) and GIT are installed. Then:\n```\ngit clone https://github.com/shinomakoi/magi_llm_gui\ncd magi_llm_gui\n```\nOptionally create a virtual environment (recommended)\n\n```\npython -m venv .magi_venv\nsource ./.magi_venv/bin/activate ### For Linux\n.\\.magi_venv\\Scripts\\activate ## For Windows\n```\n```\npip install -r requirements.txt\n```\n**llama.cpp**\n\nllama-cpp-python is included as a backend for CPU, but you can optionally install with GPU support, e.g. ```CMAKE_ARGS=\"-DLLAMA_CUBLAS=on\" FORCE_CMAKE=1 pip install llama-cpp-python``` for CUDA acceleration. \nSee: \nhttps://github.com/abetlen/llama-cpp-python/#installation-with-openblas--cublas--clblast--metal\n\nCan also use the llama.cpp server API if it's launched. See: https://github.com/ggerganov/llama.cpp/tree/master/examples/server\n\n**Exllama**\n\nTo install Exllama, follow the install instructions at https://github.com/turboderp/exllama inside the magi_llm_gui folder. Also requires CUDA Toolkit installed (installed with Linux package manager or downloaded from NVIDIA for Windows).\n```\npip install --pre torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/cu118\npip install safetensors sentencepiece ninja\ngit clone https://github.com/turboderp/exllama\n```\n\n**Usage:**\n\nTo launch the Magi LLM GUI, use: \n```\npython magi_llm_app.py\n```\nYou can set the generation parameters in Settings \u003e Parameters\n![image](https://github.com/shinomakoi/magi_llm_gui/assets/112139428/b02af911-e7eb-4353-a9f4-7b1f1f23bfe2)\n\nUses https://github.com/abetlen/llama-cpp-python for llama.cpp support\n\nUses https://github.com/UN-GCPDS/qt-material for themes\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fshinomakoi%2Fmagi_llm_gui","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fshinomakoi%2Fmagi_llm_gui","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fshinomakoi%2Fmagi_llm_gui/lists"}