bge-reranker-v2-m3
Official · BF16 · safetensors
Runtime certified: Transformers Sentence-transformers Flagembedding
| Precision / quantization | Format | Bits | Publisher trust | Deployment state |
|---|---|---|---|---|
| BF16 | safetensors | 16 | Official | Runtime certified |
BGE · Reranking · BGE Reranker v2 M3
BGE Reranker v2 M3: Specs, GPU requirements, hosting & deployment
BGE Reranker v2 M3 is a current Reranking release in the BGE family, certified from its immutable official source revision.
Total parameters568M
Active parametersN/A / Not directly comparable
Context window8,192 tokens
Release statusCurrent · Current
ArchitectureMultilingual reranking transformer
ModalitiesText
LicenseApache License 2.0
Deployment stateDeployable with certified configuration
Commercial stateCommercial Use Allowed
Release date2024-03-15
Architecture, strengths and use cases
BGE Reranker v2 M3 is an official self-hostable BAAI Embedding and reranking release. It uses Multilingual reranking transformer with 0.568B. Exact checkpoint, license, runtime, and hardware evidence is tied to the verified upstream revision.
BGE Reranker v2 M3 uses Multilingual reranking transformer with 0.568B. Pipeline and configuration fields are reported only where the official source publishes them.
Verified Multilingual reranking transformer architecture
Official checkpoint and pipeline evidence
Official BF16, Unknown checkpoint coverage
Self-hosted Embedding and reranking workloads
Controlled model evaluation
Production deployment planning
Certified checkpoints and quantizations
Only exact, source-certified variants attached to this release are shown.
Recommended hardware
Use only the listed runtime configurations with the exact checkpoint precision. Hardware sizing considers resident pipeline memory, runtime overhead, input and output dimensions, batch size, and safety headroom.
Estimated weight memory1.09 GB
Runtime overhead4.92 GB
Total with safety margin7.45 GB
Recommended best value
1× NVIDIA A100 SXM 80GB
80 GB total VRAM · nvlink
72.55 GB headroom · Available
USD 915 / monthLowest-cost viable
1× NVIDIA L4 24GB
24 GB total VRAM · pcie
16.55 GB headroom · Available
USD 250 / monthHighest performance
1× NVIDIA H200 SXM 141GB
141 GB total VRAM · nvswitch
133.55 GB headroom · Limited capacity
USD 2,345 / monthLicense and self-hosting considerations
The exact pipeline and selected precision must fit on the chosen GPUs. Requirements vary with resolution, duration, batch size, modalities, and runtime; language-model KV-cache rules are not applied.
BGE Reranker v2 M3 is published under Apache License 2.0. The release-scoped official license link and verification date are retained with the catalogue record.
Commercial Use Allowed. The official license permits commercial use; its obligations still apply.
Alternatives and sibling variants
bge-reranker-v2-m3
Release timeline
baai/bge/bge-reranker-v2-m3 @ a0f5b78dcaca3b947f9c3996ca54b10da5328cdf462272540df0913655985770
Frequently asked questions
How much VRAM does BGE Reranker v2 M3 require?
The estimate uses the certified checkpoint, precision, runtime, workload dimensions, batch size, and domain-specific overhead.
Which runtimes support BGE Reranker v2 M3?
Certified upstream runtime evidence is available for transformers, sentence-transformers, flagembedding.
Can BGE Reranker v2 M3 be used commercially?
The stored commercial classification is Commercial Use Allowed. Consult the official Apache License 2.0 terms for the final obligations.
Official references
Last verified: 2026-08-26