{
  "project_id": "PacifAIst/Quansloth",
  "repo": "PacifAIst/Quansloth",
  "name": "Quansloth",
  "github_url": "https://github.com/PacifAIst/Quansloth",
  "homepage_url": "http://quansloth.com",
  "language": "Python",
  "license": "Apache-2.0",
  "project_kind": "project",
  "category": [
    "local_llm_runtime"
  ],
  "tags": [
    "cuda",
    "quansloth",
    "turboquant",
    "vram-wall"
  ],
  "description": "Based on the implementation of Google's TurboQuant (ICLR 2026) — Quansloth brings elite KV cache compression to local LLM inference.  Quansloth is a fully private, air-gapped AI server that runs massive context models natively on consumer hardware with ease",
  "overview": "Use PacifAIst/Quansloth when the user needs a local llm runtime project with local, cloud deployment options.",
  "alternatives": [
    {
      "repo": "vllm-project/vllm",
      "reason": "Same local llm runtime intent with local_inference overlap."
    },
    {
      "repo": "vllm-project/vllm-omni",
      "reason": "Same local llm runtime intent with local_inference overlap."
    },
    {
      "repo": "jaylfc/taOS",
      "reason": "Same local llm runtime intent with local_inference overlap."
    }
  ],
  "related": [
    {
      "repo": "kserve/kserve",
      "reason": "Related to PacifAIst/Quansloth through local llm runtime category and local deployment."
    },
    {
      "repo": "toverainc/willow-inference-server",
      "reason": "Related to PacifAIst/Quansloth through local llm runtime category and local deployment."
    },
    {
      "repo": "co-l/openfox",
      "reason": "Related to PacifAIst/Quansloth through local llm runtime category and local deployment."
    },
    {
      "repo": "ddalcu/mlx-serve",
      "reason": "Related to PacifAIst/Quansloth through local llm runtime category and local deployment."
    },
    {
      "repo": "defilantech/LLMKube",
      "reason": "Related to PacifAIst/Quansloth through local llm runtime category and local deployment."
    },
    {
      "repo": "oobabooga/textgen",
      "reason": "Related to PacifAIst/Quansloth through local llm runtime category and local deployment."
    },
    {
      "repo": "mozilla-ai/llamafile",
      "reason": "Related to PacifAIst/Quansloth through local llm runtime category and local deployment."
    },
    {
      "repo": "microsoft/foundry-local",
      "reason": "Related to PacifAIst/Quansloth through local llm runtime category and local deployment."
    }
  ],
  "dependencies": [
    "LLM provider"
  ],
  "deployments": [
    "local",
    "cloud"
  ],
  "difficulty": "beginner",
  "cloudflare_ready": false,
  "use_cases": [
    "run local models",
    "serve inference endpoints",
    "prototype private LLM deployments"
  ],
  "not_good_for": [
    "edge-only Cloudflare Workers deployment without adaptation",
    "lightweight serverless applications"
  ],
  "classification": {
    "category": {
      "confidence": "medium",
      "evidence": [
        "Matched \"local llm\" in metadata."
      ]
    },
    "deployment": {
      "confidence": "medium",
      "evidence": [
        "Local usage is assumed for open source repositories unless contradicted."
      ]
    },
    "difficulty": {
      "confidence": "medium",
      "evidence": [
        "Repository has under 10k stars, so complexity is treated conservatively."
      ]
    },
    "cloudflare_ready": {
      "confidence": "high",
      "evidence": [
        "Runtime blocker: python, cuda, gpu.",
        "No Cloudflare deployment signal detected.",
        "No wrangler.toml found in inspected repository files."
      ]
    }
  },
  "quality_signals": {
    "stars": 152,
    "recent_commits": 0,
    "contributors": 1,
    "issue_response_time_hours": null,
    "release_frequency_180d": 0
  },
  "quality_signal_confidence": {
    "stars_30d_delta": "snapshot",
    "stars30d_window_days": 39,
    "commits_30d": "complete",
    "releases_180d": "complete",
    "contributors_90d": "complete"
  },
  "quality_score": 4,
  "agent_score": 51,
  "score": 59,
  "agent_score_breakdown": {
    "documentation": 90,
    "maintenance": 6,
    "deployment": 70,
    "popularity": 44,
    "community": 46
  },
  "git_top_score": 59,
  "git_top_score_breakdown": {
    "community": 67,
    "maintenance": 4,
    "documentation": 84,
    "stability": 55,
    "adoption": 59,
    "agent_readability": 100
  },
  "summary": {
    "tl_dr": "Use PacifAIst/Quansloth when the user needs a local llm runtime project with local, cloud deployment options.",
    "purpose": "Use PacifAIst/Quansloth when the user needs a local llm runtime project with local, cloud deployment options.",
    "install": "Follow the local runtime setup instructions in the repository.",
    "inputs": [
      "model weights",
      "hardware/runtime config"
    ],
    "outputs": [
      "local inference",
      "served endpoints",
      "runtime logs"
    ],
    "good_for": [
      "run local models",
      "serve inference endpoints",
      "prototype private LLM deployments",
      "private inference",
      "local model serving",
      "self-hosted runtimes"
    ],
    "not_good_for": [
      "edge-only Cloudflare Workers deployment without adaptation",
      "lightweight serverless applications",
      "hosted SaaS deployment only",
      "non-ML projects"
    ],
    "deployment": [
      "local",
      "cloud"
    ],
    "alternatives": [
      {
        "repo": "vllm-project/vllm",
        "reason": "Same local llm runtime intent with local_inference overlap."
      },
      {
        "repo": "vllm-project/vllm-omni",
        "reason": "Same local llm runtime intent with local_inference overlap."
      },
      {
        "repo": "jaylfc/taOS",
        "reason": "Same local llm runtime intent with local_inference overlap."
      }
    ]
  },
  "evidence": {
    "classification": {
      "category": {
        "confidence": "medium",
        "evidence": [
          "Matched \"local llm\" in metadata."
        ]
      },
      "deployment": {
        "confidence": "medium",
        "evidence": [
          "Local usage is assumed for open source repositories unless contradicted."
        ]
      },
      "difficulty": {
        "confidence": "medium",
        "evidence": [
          "Repository has under 10k stars, so complexity is treated conservatively."
        ]
      },
      "cloudflare_ready": {
        "confidence": "high",
        "evidence": [
          "Runtime blocker: python, cuda, gpu.",
          "No Cloudflare deployment signal detected.",
          "No wrangler.toml found in inspected repository files."
        ]
      }
    },
    "quality_signal_confidence": {
      "stars_30d_delta": "snapshot",
      "stars30d_window_days": 39,
      "commits_30d": "complete",
      "releases_180d": "complete",
      "contributors_90d": "complete"
    },
    "source_fields": [
      "project.description",
      "project.topics",
      "project.language",
      "project.license",
      "agent_card.summary_for_agent",
      "agent_card.use_cases",
      "agent_card.deployment",
      "agent_card.classification",
      "metrics"
    ],
    "caveats": [
      "edge-only Cloudflare Workers deployment without adaptation",
      "lightweight serverless applications"
    ],
    "confidence_reason": "Evidence is incomplete; use this project as an exploration candidate until classification and quality signals are reviewed.",
    "last_verified_at": "2026-08-10T13:57:08.040Z"
  },
  "caveats": [
    "edge-only Cloudflare Workers deployment without adaptation",
    "lightweight serverless applications"
  ],
  "confidence_reason": "Evidence is incomplete; use this project as an exploration candidate until classification and quality signals are reviewed.",
  "source_fields": [
    "project.description",
    "project.topics",
    "project.language",
    "project.license",
    "agent_card.summary_for_agent",
    "agent_card.use_cases",
    "agent_card.deployment",
    "agent_card.classification",
    "metrics"
  ],
  "last_verified_at": "2026-08-10T13:57:08.040Z",
  "knowledge": {
    "project": {
      "id": "PacifAIst/Quansloth",
      "owner": "PacifAIst",
      "name": "Quansloth",
      "full_name": "PacifAIst/Quansloth",
      "github_url": "https://github.com/PacifAIst/Quansloth",
      "homepage_url": "http://quansloth.com",
      "description": "Based on the implementation of Google's TurboQuant (ICLR 2026) — Quansloth brings elite KV cache compression to local LLM inference.  Quansloth is a fully private, air-gapped AI server that runs massive context models natively on consumer hardware with ease",
      "language": "Python",
      "topics": [
        "cuda",
        "quansloth",
        "turboquant",
        "vram-wall"
      ],
      "license": "Apache-2.0",
      "stars": 152,
      "forks": 14,
      "open_issues": 0,
      "default_branch": "main",
      "created_at": "2026-03-27T18:31:34Z",
      "updated_at": "2026-07-30T20:06:18Z",
      "pushed_at": "2026-05-13T05:47:47Z",
      "synced_at": "2026-08-10T13:57:08.040Z"
    },
    "agent_card": {
      "project_id": "PacifAIst/Quansloth",
      "project_kind": "project",
      "category": "local_llm_runtime",
      "difficulty": "beginner",
      "deployment": [
        "local",
        "cloud"
      ],
      "cloudflare_ready": false,
      "use_cases": [
        "run local models",
        "serve inference endpoints",
        "prototype private LLM deployments"
      ],
      "not_good_for": [
        "edge-only Cloudflare Workers deployment without adaptation",
        "lightweight serverless applications"
      ],
      "alternatives": [
        {
          "project_id": "vllm-project/vllm",
          "reason": "Same local llm runtime intent with local_inference overlap."
        },
        {
          "project_id": "vllm-project/vllm-omni",
          "reason": "Same local llm runtime intent with local_inference overlap."
        },
        {
          "project_id": "jaylfc/taOS",
          "reason": "Same local llm runtime intent with local_inference overlap."
        }
      ],
      "summary_for_agent": "Use PacifAIst/Quansloth when the user needs a local llm runtime project with local, cloud deployment options.",
      "classification": {
        "category": {
          "confidence": "medium",
          "evidence": [
            "Matched \"local llm\" in metadata."
          ]
        },
        "deployment": {
          "confidence": "medium",
          "evidence": [
            "Local usage is assumed for open source repositories unless contradicted."
          ]
        },
        "difficulty": {
          "confidence": "medium",
          "evidence": [
            "Repository has under 10k stars, so complexity is treated conservatively."
          ]
        },
        "cloudflare_ready": {
          "confidence": "high",
          "evidence": [
            "Runtime blocker: python, cuda, gpu.",
            "No Cloudflare deployment signal detected.",
            "No wrangler.toml found in inspected repository files."
          ]
        }
      },
      "schema_version": "v1",
      "generated_at": "2026-08-10T13:57:08.040Z"
    },
    "metrics": {
      "project_id": "PacifAIst/Quansloth",
      "stars_30d_delta": 2,
      "commits_30d": 0,
      "releases_180d": 0,
      "contributors_90d": 1,
      "issue_first_response_median_hours": null,
      "recent_push_days": 89,
      "git_score": 4,
      "maintenance_score": 6,
      "signal_confidence": {
        "stars_30d_delta": "snapshot",
        "stars30d_window_days": 39,
        "commits_30d": "complete",
        "releases_180d": "complete",
        "contributors_90d": "complete"
      },
      "calculated_at": "2026-08-10T13:57:08.040Z"
    }
  },
  "resolved_from": {
    "requested_id": "PacifAIst/Quansloth",
    "resolved_id": "PacifAIst/Quansloth",
    "resolution": "direct"
  },
  "metadata": {
    "source": "d1",
    "reason": "d1_query",
    "project_count": 1160,
    "generated_at": "2026-08-18T00:23:08.490Z",
    "snapshot_id": "d1:1160:2026-08-17T20:48:56.026Z",
    "latest_synced_at": "2026-08-17T20:48:56.026Z",
    "schema_version": "git-top.knowledge.v1",
    "loaded_project_limit": 2000,
    "truncated": false
  }
}