// BGE embeddings & rerankers · Reranker
bge-reranker-v2.5-gemma2-lightweight: VRAM & local deployment
9.24B parameters. About 6.7 GB at 4-bit and 20.8 GB at BF16.
released 2024-07-25licence: Commercial with conditionsmemory figures are estimates
01Specs
| Publisher | BAAI · BAAI |
|---|---|
| Family / series | BGE embeddings & rerankers · bge-reranker-gemma2-lightweight |
| Type | Reranker (text-classification) |
| Parameters | 9.24B Source: counted from official safetensors weights |
| Released weights | FP32 · 37.0 GBdownload |
| Licence | Gemma Terms of Use · Commercial with conditionsCommercial use allowed under the publisher’s own licence terms (user caps, acceptable-use policy, attribution or region limits). Read it before shipping. |
| Released | 2024-07-25 (Hugging Face repo created) |
02How much VRAM it needs (estimate)
Rerankers are small; memory grows with batch size and sequence length.
| Precision | Weights | Weights + overhead | Smallest GPU | Mac |
|---|---|---|---|---|
| BF16 / FP16 (original) | 18.5 GB | 20.8 GB | RTX 4090 24GB | Mac 36GB |
| FP8 / INT8 / Q8_0 | 9.8 GB | 11.3 GB | 16GB GPU | Mac 24GB |
| 4-bit (Q4_K_M / AWQ / GPTQ-Int4) | 5.6 GB | 6.7 GB | 8GB GPU | Mac 16GB |
Bits per weight: BF16 16, FP8 8.5, 4-bit 4.85. “Fits” = total ≤ 90% of memory; Mac GPU can use ~2/3 of unified memory (≤36GB) or ~3/4 (larger). For MoE, all experts must be in memory, so size by total parameters. Method →
03How to run it
Only runtimes the publisher or the runtime’s official library names for this model.
- Transformers — mentioned in the official model card
- Sentence Transformers — mentioned in the official model card
04Official repositories & quantised builds
1 official repo(s) from BAAI.
05Other BGE embeddings & rerankers models
All 8 →| Model | Params | 4-bit total | Released |
|---|---|---|---|
| bge-code-v1 | 1.54B | 1.5 GB | 2025-05-15 |
| BGE-VL-base | 150M | 0.6 GB | 2025-02-25 |
| BGE-VL-large | 428M | 0.8 GB | 2025-02-25 |
| bge-en-icl | 7.11B | 5.2 GB | 2024-07-25 |
| bge-multilingual-gemma2 | 9.24B | 6.7 GB | 2024-07-25 |
| bge-reranker-v2-m3 | 568M | 0.9 GB | 2024-03-15 |
| bge-m3 | — | — | 2024-01-27 |
06Sources
Data checked 2024-09-06. Parameters, context and licence are copied from the official repository; memory figures are our estimates.