id: BAAI__bge-m3__candidate
status: verified
name: bge-m3
org: BAAI
source:
  kind: huggingface
  url: https://huggingface.co/BAAI/bge-m3
  revision: main
  model_card_url: https://huggingface.co/BAAI/bge-m3
  project_url: https://github.com/FlagOpen/FlagEmbedding
license:
  spdx: MIT
  url: https://huggingface.co/BAAI/bge-m3
  allows_offline_retention: true
  allows_local_ops: true
  allows_fine_tune: true
  notes: ""
profile:
  summary: "Default multilingual dense embedding model for local RAG."
  original_source: https://huggingface.co/BAAI/bge-m3
  use_cases:
    - "NetKingdom / Coulomb document and wiki retrieval"
    - "Multilingual (DE/EN/…) semantic search"
    - "Hybrid retrieval experiments (dense + multi-granularity features)"
    - "Offline RAG in sandboxed agents"
    - "Indexing ops runbooks and code comments"
  sweet_spots:
    - "Self-hosted production-quality multilingual embed"
    - "MIT license; easy ops story"
    - "Strong general retrieval without API spend"
    - "Pairs cleanly with a small cross-encoder reranker"
  not_ideal_for:
    - "Generation / chat (not an LLM)"
    - "Pure code retrieval if a code-specialized embed clearly wins A/B"
    - "Ultra-tiny edge when EmbeddingGemma-class is enough"
  capability_notes: >
    BAAI BGE-M3 is a staple open embedder: multi-lingual, multi-granularity,
    widely deployed for RAG. Primary R-tier retrieval backbone for the lab.
swot:
  strengths:
    - "Proven multilingual retrieval quality for self-host"
    - "MIT; small enough for CPU/GPU flexibility"
    - "Mature FlagEmbedding ecosystem"
  weaknesses:
    - "Not optimized solely for code or for extreme long-context embed niches"
    - "Newer embed lines (Qwen/Gemma/Nomic) may win specific A/B tests"
  opportunities:
    - "Domain-adapted embed fine-tune on Coulomb corpora later"
    - "Companion bge-reranker for precision@k gains"
  threats:
    - "Leaderboard churn; risk of holding a stale 'default' without re-eval"
    - "Pipeline lock-in if vector DBs assume fixed dimension without migration plan"
artifacts:
  - path: "pytorch_model.bin"
    sha256: "b5e0ce3470abf5ef3831aa1bd5553b486803e83251590ab7ff35a117cf6aad38"
    bytes: 2271145830
  - path: "sentencepiece.bpe.model"
    sha256: "cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865"
    bytes: 5069051
  - path: "tokenizer.json"
    sha256: "21106b6d7dab2952c1d496fb21d5dc9db75c28ed361a05f5020bbba27810dd08"
    bytes: 17098108
size:
  total_bytes: 2293331623
  total_human: "2.14 GiB"
hardware_class:
  min_vram_gb_q4: 1
  min_vram_gb_fp16: 2
  notes: "Runs on CPU comfortably for many workloads"
axes: [B]
priority: high
collection:
  approved_by: "bernd"
  approved_at: "2026-07-28"
  downloaded_at: "2026-07-28"
  downloaded_by: "grok"
  storage_path: "/mnt/d/vault/coulomb/freedom-intelligence/models/BAAI__bge-m3/main"
  brief_refs:
    - research/2026-07-24-baseline-field-survey.md
reason: "P0/R multilingual embedding staple for local RAG (docs, ops notes, DE/EN)."
tags: [tier-r, embedding, multilingual, rag]
companions:
  - BAAI__bge-reranker-v2-m3__candidate
notes: "Small download — within agent auto-collect band after license check once storage pinned."
history:
  - at: "2026-07-24"
    event: nominated
    by: baseline-survey
    detail: "P0 recommendation from initial deep research."
  - at: "2026-07-24"
    event: profile_swot_added
    by: grok
    detail: "schema 0.2 profile + SWOT."
  - at: "2026-07-28"
    event: approved
    by: bernd
    detail: "R multilingual embed"
  - at: "2026-07-28"
    event: collected
    by: grok
    detail: "snapshot_download weights-only to VAULT"
  - at: "2026-07-28"
    event: verified
    by: grok
    detail: "MANIFEST.json sha256 for weight files"