BAAI · Embeddings and rerank · 568M parameters · Apache-2.0
bge-reranker-v2-m3
Needs 1 GB at FP8 / INT8. The smallest real configuration today is 1× Quadro P2000 at Vast.ai, $0.03 per hour, about $22 a month at 730 hours.
Parameters568Mdense
Context8k tokensmaximum published
Checkpoint2 GBFP32, as published
LicenseApache-2.0check before commercial use
ReleasedMar 15, 2024documented date
Smallest configuration · FP8 / INT8
1× Quadro P20005 GB VRAM · 14% used
- Per hour
- $0.03
- Per month
- $22
- Cheapest at
Vast.ai
What is documented about bge-reranker-v2-m3
news checked 2026-10-2714.6M downloads/month, the most-used open reranker, but missing from the 2026-10-04 catalogue. Date = HF repo creation.
- https://huggingface.co/BAAI/bge-reranker-v2-m3
- https://huggingface.co/api/models/BAAI/bge-reranker-v2-m3?blobs=true
Memory · 3 precisions · 3 context lengthsHow much VRAM it needs
Weights plus runtime overhead, then the KV cache that grows with the context you serve.
| Precision | Weights | Weights + headroom | 4k context | 8k context |
|---|---|---|---|---|
| FP32published checkpoint | 2 GB | 3 GB | 4 GB | 4 GB |
| FP8 / INT8estimated | 1 GB | 1 GB | 2 GB | 2 GB |
| INT4 / MXFP4estimated | 0 GB | 1 GB | 1 GB | 2 GB |
| KV cacheone sequence, FP16 cache, included above | — | — | 1 GB | 1 GB |
Cross-checked on Hugging Face Oct 28, 2026: 0.57B parameters in the safetensors headers, 2.3 GB of weight files, attention layout from config.json (24 layers, 16 KV heads × 64). Method: weights as published at the native precision, verified on Hugging Face 2026-10-28; other precisions estimated at 1 (8-bit) and 0.6 (4-bit) bytes per parameter; × 1.2 runtime headroom; KV cache = 4096 bytes per token per layer × 24 full-attention layers (FP16 cache, one sequence).config.json ↗
Smallest configuration per GPU · 109 GPUs · cheapest eligible on-demand offer per GPU count, every provider on fileWhat it costs to run, GPU by GPU
The fewest GPUs of one type whose total memory fits the model at short context, priced from the cheapest eligible on-demand offer for exactly that count (45-day window, newest reading per provider), with the next providers beside it. Monthly = 730 hours.
| GPU | Smallest config | VRAM used | $ / hour | $ / month | Cheapest at |
|---|---|---|---|---|---|
| Quadro P2000Best fit | 1× 5 GB5 GB total | 14% | $0.03 | $22 | Vast.aiTrust 78 · read Nov 2 · receipt |
| RTX 3060 | 1× 12 GB12 GB total | 6% | $0.04 | $26 | Vast.aiTrust 78 · read Nov 2 · receipt · also Clore.ai $0.05, gcube $0.05 |
| RTX A2000 | 1× 12 GB12 GB total | 6% | $0.04 | $26 | Vast.aiTrust 78 · read Nov 2 · receipt · also gcube $0.09, Runpod $0.12 |
| GTX 1660 Ti | 1× 6 GB6 GB total | 11% | $0.04 | $26 | Vast.aiTrust 78 · read Nov 2 · receipt · also Theta EdgeCloud $0.12 |
| GTX 1050 | 1× 2 GB2 GB total | 34% | $0.04 | $27 |  Clore.aiTrust 49 · read Nov 2 · receipt · also Akash Network $0.14 |
| Tesla P4 | 1× 8 GB8 GB total | 9% | $0.04 | $29 | Vast.aiTrust 78 · read Nov 2 · receipt · also Akash Network $0.06, gcube $0.07 |
| T4 | 1× 16 GB16 GB total | 4% | $0.04 | $29 | Vast.aiTrust 78 · read Nov 2 · receipt · also iwinv $0.20, Theta EdgeCloud $0.20 |
| GTX 1060 | 1× 6 GB6 GB total | 11% | $0.04 | $30 | Vast.aiTrust 78 · read Nov 2 · receipt |
| GTX 1660 | 1× 6 GB6 GB total | 11% | $0.04 | $30 | Vast.aiTrust 78 · read Nov 2 · receipt · also Edgevana $0.78 |
| Tesla P40 | 1× 24 GB24 GB total | 3% | $0.04 | $30 | Clore.aiTrust 49 · read Nov 2 · receipt · also gcube $0.07, Vast.ai $0.11 |
| GTX Titan X | 1× 12 GB12 GB total | 6% | $0.04 | $31 | Vast.aiTrust 78 · read Nov 2 · receipt |
| Titan Xp | 1× 12 GB12 GB total | 6% | $0.04 | $31 | Vast.aiTrust 78 · read Nov 2 · receipt |
| GTX 1080 | 1× 8 GB8 GB total | 9% | $0.04 | $32 | Vast.aiTrust 78 · read Nov 2 · receipt · also Edgevana $0.06 |
| Tesla P100 | 1× 16 GB16 GB total | 4% | $0.04 | $33 | Vast.aiTrust 78 · read Nov 2 · receipt · also gcube $0.07 |
| RTX 2060 | 1× 6 GB6 GB total | 11% | $0.04 | $33 | |
| GTX 1650 | 1× 4 GB4 GB total | 17% | $0.05 | $35 | Vast.aiTrust 78 · read Nov 2 · receipt |
| GTX 1070 | 1× 8 GB8 GB total | 9% | $0.05 | $36 | Vast.aiTrust 78 · read Nov 2 · receipt · also Clore.ai $0.08 |
| GTX 1660 Super | 1× 6 GB6 GB total | 11% | $0.05 | $38 |  Theta EdgeCloudnot scored · read Nov 2 · receipt |
| Quadro P4000 | 1× 8 GB8 GB total | 9% | $0.06 | $40 | Vast.aiTrust 78 · read Nov 2 · receipt · also Edgevana $0.08 |
| RTX 2070 | 1× 8 GB8 GB total | 9% | $0.06 | $41 | Vast.aiTrust 78 · read Nov 2 · receipt · also gcube $0.06, Clore.ai $0.21 |
| RTX 3060 Ti | 1× 8 GB8 GB total | 9% | $0.06 | $41 | Vast.aiTrust 78 · read Nov 2 · receipt · also Clore.ai $0.06, gcube $0.06 |
| RTX 2060 Super | 1× 8 GB8 GB total | 9% | $0.06 | $41 | |
| GTX 1070 Ti | 1× 8 GB8 GB total | 9% | $0.06 | $44 | Vast.aiTrust 78 · read Nov 2 · receipt · also Clore.ai $0.10 |
| RTX 2070 Super | 1× 8 GB8 GB total | 9% | $0.06 | $44 | |
| The 24 cheapest of 109 GPU types that fit. Every GPU, any precision and context, in the finder | |||||
bge-reranker-v2-m3 · related