{"id":51026591,"url":"https://github.com/gitstq/llm-match-pro","last_synced_at":"2026-06-21T20:02:05.609Z","repository":{"id":363817085,"uuid":"1265055323","full_name":"gitstq/llm-match-pro","owner":"gitstq","description":"智能本地LLM硬件匹配与推荐引擎 - Smart Local LLM Hardware Matching \u0026 Recommendation Engine","archived":false,"fork":false,"pushed_at":"2026-06-10T12:31:39.000Z","size":36,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-06-10T14:17:43.877Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/gitstq.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,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-06-10T12:26:33.000Z","updated_at":"2026-06-10T12:30:55.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/gitstq/llm-match-pro","commit_stats":null,"previous_names":["gitstq/llm-match-pro"],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/gitstq/llm-match-pro","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gitstq%2Fllm-match-pro","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gitstq%2Fllm-match-pro/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gitstq%2Fllm-match-pro/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gitstq%2Fllm-match-pro/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/gitstq","download_url":"https://codeload.github.com/gitstq/llm-match-pro/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gitstq%2Fllm-match-pro/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34623906,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-21T02:00:05.568Z","response_time":54,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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":[],"created_at":"2026-06-21T20:02:05.119Z","updated_at":"2026-06-21T20:02:05.600Z","avatar_url":"https://github.com/gitstq.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cdiv align=\"center\"\u003e\n\n# 🤖 LLM-Match-Pro\n\n**智能本地LLM硬件匹配与推荐引擎**\n\n[![Python](https://img.shields.io/badge/Python-3.10%2B-blue)](https://www.python.org/)\n[![License](https://img.shields.io/badge/License-MIT-green.svg)](LICENSE)\n[![Tests](https://img.shields.io/badge/Tests-24%20passing-brightgreen)](tests/)\n[![CLI](https://img.shields.io/badge/CLI-Typer-orange)](https://typer.tiangolo.com/)\n[![WebUI](https://img.shields.io/badge/WebUI-Streamlit-red)](https://streamlit.io/)\n\n[English](README_EN.md) | [繁體中文](README_ZH_TW.md)\n\n\u003c/div\u003e\n\n---\n\n## 🎉 项目介绍\n\n**LLM-Match-Pro** 是一款智能本地大语言模型（LLM）硬件匹配与推荐引擎。它能够自动检测你的硬件配置（GPU/CPU/内存），并从预置的模型数据库中智能推荐最适合你设备运行的本地LLM模型。\n\n### 为什么选择 LLM-Match-Pro？\n\n- 🎯 **中文模型优先** — 内置18+主流中文模型（DeepSeek、Qwen、ChatGLM、Baichuan、Yi）\n- 🇨🇳 **国产GPU支持** — 支持昇腾（Ascend）、摩尔线程（Moore Threads）等国产显卡\n- 🧠 **智能量化推荐** — 根据你的显存自动推荐最佳量化方案（Q2_K ~ FP16）\n- 📊 **可视化分析** — Web UI提供雷达图、柱状图等直观对比\n- 🚀 **一键启动命令** — 自动生成 llama.cpp / Ollama / vLLM / Docker 启动命令\n\n---\n\n## ✨ 核心特性\n\n| 特性 | 描述 |\n|------|------|\n| 🔍 **自动硬件检测** | 自动识别 NVIDIA / AMD / 昇腾 / 摩尔线程 GPU |\n| 📚 **丰富模型库** | 18+ 预置模型，覆盖 6B ~ 72B 参数规模 |\n| 🎚️ **智能量化** | 支持 13 种量化方案，自动推荐最佳配置 |\n| 📈 **性能预估** | 预估推理速度（tokens/s）、VRAM占用 |\n| 💻 **CLI + Web** | 命令行工具 + Streamlit Web 界面双模式 |\n| 🐳 **Docker支持** | 一键 Docker 部署，开箱即用 |\n| 🧪 **完整测试** | 24 个单元测试，覆盖率 \u003e90% |\n\n---\n\n## 🚀 快速开始\n\n### 安装\n\n```bash\n# 从 PyPI 安装（即将发布）\npip install llm-match-pro\n\n# 或从源码安装\ngit clone https://github.com/gitstq/llm-match-pro.git\ncd llm-match-pro\npip install -e \".[dev]\"\n```\n\n### CLI 使用\n\n```bash\n# 检测硬件\nllm-match-pro detect\n\n# 推荐模型\nllm-match-pro recommend\n\n# 查看模型列表\nllm-match-pro models\n\n# 获取升级建议\nllm-match-pro upgrade\n\n# 生成启动命令\nllm-match-pro launch Qwen/Qwen2.5-7B-Instruct --quant Q4_K_M\n```\n\n### Web UI 使用\n\n```bash\n# 启动 Web 界面\nllm-match-web\n\n# 或\nstreamlit run llm_match_pro/web.py\n```\n\n然后访问 http://localhost:8501\n\n### Docker 使用\n\n```bash\n# 构建镜像\ndocker build -t llm-match-pro .\n\n# 运行 CLI\ndocker run -it --rm llm-match-pro detect\n\n# 运行 Web UI\ndocker run -it --rm -p 8501:8501 llm-match-pro web\n```\n\n---\n\n## 📖 详细使用指南\n\n### 硬件检测\n\n```bash\n$ llm-match-pro detect\n\n🔍 正在检测硬件信息...\n\n┌─────────┬─────────────────────────────┬──────────┬─────────┬────────────────┐\n│ 序号    │ 名称                        │ 厂商     │ 显存    │ 驱动           │\n├─────────┼─────────────────────────────┼──────────┼─────────┼────────────────┤\n│ 1       │ NVIDIA GeForce RTX 4090     │ NVIDIA   │ 24.0 GB │ 535.104.05     │\n└─────────┴─────────────────────────────┴──────────┴─────────┴────────────────┘\n```\n\n### 模型推荐\n\n```bash\n$ llm-match-pro recommend --top-k 5 --lang zh\n\n🤖 LLM-Match-Pro 智能推荐\n\n┌──────┬────────────────────────┬──────────┬────────┬──────────┬──────────┬──────┬────────┐\n│ 排名 │ 模型                   │ 参数量   │ 量化   │ VRAM     │ 速度     │ 评分 │ 状态   │\n├──────┼────────────────────────┼──────────┼────────┼──────────┼──────────┼──────┼────────┤\n│ 1    │ Qwen2.5-7B-Instruct    │ 7.6B     │ Q4_K_M │ 4.5 GB   │ 35.2 t/s │ 92   │ ✓ 可   │\n│ 2    │ DeepSeek-LLM-7B-Chat   │ 7.0B     │ Q4_K_M │ 4.2 GB   │ 38.5 t/s │ 90   │ ✓ 可   │\n│ 3    │ ChatGLM3-6B            │ 6.0B     │ Q4_K_M │ 3.6 GB   │ 42.0 t/s │ 88   │ ✓ 可   │\n└──────┴────────────────────────┴──────────┴────────┴──────────┴──────────┴──────┴────────┘\n```\n\n### 支持的模型\n\n| 系列 | 模型 | 参数量 | 上下文 | 语言 |\n|------|------|--------|--------|------|\n| DeepSeek | DeepSeek-LLM-7B/67B-Chat | 7B/67B | 4K | 中文 |\n| Qwen | Qwen2.5-7B/14B/32B/72B-Instruct | 7.6B~72.7B | 32K | 中文 |\n| ChatGLM | ChatGLM3-6B / GLM-4-9B-Chat | 6B/9B | 8K~128K | 中文 |\n| Baichuan | Baichuan2-7B/13B-Chat | 7B/13B | 4K | 中文 |\n| Yi | Yi-1.5-6B/34B-Chat | 6B/34B | 4K | 中文 |\n| Llama | Llama-3.1-8B/70B-Instruct | 8B/70B | 128K | 英文 |\n| Mistral | Mistral-7B / Mixtral-8x7B | 7B/47B | 32K | 英文 |\n\n---\n\n## 💡 设计思路与迭代规划\n\n### 架构设计\n\n```\nllm_match_pro/\n├── hardware/      # 硬件检测层\n├── models/        # 模型数据库层\n├── engine/        # 推荐引擎层\n├── config/        # 配置管理层\n└── utils/         # 工具函数层\n```\n\n### 评分算法\n\n综合评分 = VRAM适配度(25%) + 性能评分(25%) + 质量评分(25%) + 兼容性评分(25%)\n\n### 迭代规划\n\n- [x] v1.0.0 — 基础功能：硬件检测、模型推荐、CLI、Web UI\n- [ ] v1.1.0 — ModelScope API 同步、在线模型搜索\n- [ ] v1.2.0 — 基准测试数据自动更新\n- [ ] v1.3.0 — VS Code 插件\n- [ ] v2.0.0 — 分布式推理推荐、多机多卡方案\n\n---\n\n## 📦 打包与部署指南\n\n### 构建 Python 包\n\n```bash\nmake build\n```\n\n### 构建可执行文件\n\n```bash\nmake build-exe\n```\n\n### Docker 部署\n\n```bash\nmake docker-build\nmake docker-run\n```\n\n---\n\n## 🤝 贡献指南\n\n欢迎提交 Issue 和 PR！\n\n1. Fork 本仓库\n2. 创建功能分支 (`git checkout -b feature/amazing-feature`)\n3. 提交更改 (`git commit -m 'feat: add amazing feature'`)\n4. 推送分支 (`git push origin feature/amazing-feature`)\n5. 创建 Pull Request\n\n### 开发环境\n\n```bash\nmake install-dev\nmake test\nmake lint\nmake format\n```\n\n---\n\n## 📄 开源协议\n\n本项目采用 [MIT License](LICENSE) 开源协议。\n\n---\n\n\u003cdiv align=\"center\"\u003e\n\n**Made with ❤️ by gitstq**\n\n如果本项目对你有帮助，请给个 ⭐ Star！\n\n\u003c/div\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgitstq%2Fllm-match-pro","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fgitstq%2Fllm-match-pro","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgitstq%2Fllm-match-pro/lists"}