bge-multilingual-gemma2

Benchmarks 2 rows

Summary generated, cited

BAAI/bge-multilingual-gemma2 is a 9.24B parameter LLM-based multilingual embedding model.^[1][2]

1. parameters human
2. “LLM-based multilingual embedding model”

Generated 2026-10-07 15:04 UTC by parasail-gemma-4-26b-a4b-it; each numeral points at the fact it rests on. Not a verdict.

What it is good at 3 use cases

Labels are evidence, not verdicts: measured a third-party leaderboard row for this model; author-reported a number the model author published in the card or eval files; structural a deterministic signal from the name, config or chat template, or a decision-model estimate. Each chip links to its source. All use cases.

• Embed text for searchmeasuredMTEB(eng, v2) partial 78.95decision-model estimate p=1.00name: bge+3 more
• Work across languagesstructuraldecision-model estimate p=0.99name: multilingual
• Run on a laptop or phonestructuralfits: single-gpu

Facts

• bge-multilingual-gemma2 has 9.24B parameters. (safetensors metadata, observed 2026-10-24)
• Context length is 8,192 tokens (8K). (config.json max_position_embeddings, observed 2026-10-24)
• License: Gemma Terms of Use (friction: attribution). Google's terms + prohibited-use policy; must pass terms downstream. (license file, observed 2026-10-24)
• Created 2024-07-25, last modified 2025-10-13. (HF API, observed 2026-10-24)

Servability

vLLM: supported · Gemma2Model · 7050ef881ff0835f6890a47db1859a24c65481d6SGLang: supported · Gemma2Model · 773cb938fe9484a8f7e7e46fb1b1fe96412c59ed

vLLM registry (7050ef881ff0835f6890a47db1859a24c65481d6) · SGLang registry (773cb938fe9484a8f7e7e46fb1b1fe96412c59ed) · Matched by architecture class name against each project's registry on main; 'supported' means the architecture is registered, not that this checkpoint was tested.

Hardware fit ESTIMATE

Weights-only memory for bge-multilingual-gemma2: params × bytes/param × 1.2 overhead. KV cache and activations are extra. How this is computed.

Weights only (params × bytes/param × 1.2 overhead); KV cache and activations extra.

Lineage

adapter: 1

Top variants (1 shown, ranked by downloads)

Repository changelog 24 commits

Where to run 1 providers · 1 endpoints

Hosted endpoints observed for bge-multilingual-gemma2, sorted by input price (USD per million tokens). Each row names its observer and date; prices change daily, so check the source before quoting.

Ranked by source signals (HN, Lobsters, authority domains, official posts) and recency. Summaries are generated from a stored copy of the article text; every sentence cites a span of that text, and nothing is shown that failed the citation check.

Papers 2

arXiv links found in the model card and its tags. "Peer-reviewed" is shown only with evidence: a published venue in OpenAlex (measured) or the authors' own journal reference on arXiv (reported).

• M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation cited in card
  Jianlv Chen, Shitao Xiao, Peitian Zhang +3 · 2024-02-05 · PDF · HF paper page (10 upvotes)
• C-Pack: Packed Resources For General Chinese Embeddings cited in card
  Shitao Xiao, Zheng Liu, Peitian Zhang +3 · 2023-09-14 · PDF · HF paper page (2 upvotes)

Similar models

• Qwen3-Embedding-8B · 7.57B
  same task (feature-extraction), more providers, permissive license
• Qwen3-Embedding-4B · 4.02B
  same task (feature-extraction), permissive license
• Qwen3-VL-Embedding-8B · 8.14B
  permissive license

Sources

• Hugging Face model repo
• HF Hub API (full)
• hub-stats parquet

Hub snapshot: 2026-10-25 · HF API: 2026-10-24 21:36 UTC · Providers: 2026-10-24 21:44 UTC · Articles: 2026-10-24 21:45 UTC · Summary: 2026-10-07 15:04 UTC · Last verified 2026-10-25