What GPU do I need to run BAAI/bge-reranker-v2.5-gemma2-lightweight?
9.2B parameters, published in F32. View on Hugging Face
bge-reranker-v2.5-gemma2-lightweight is published by BAAI on Hugging Face, with 164,523 downloads and 55 likes to date. It's a CostWiseGemmaForCausalLM model built for text-classification, published natively in F32.
VRAM required & cheapest live GPU fit
Required VRAM = weight size at each precision, plus a fixed overhead for KV-cache, activations, and fragmentation. Full formula and assumptions: methodology.
A GPU is only matched to a row if its hardware supports that precision, and the primary recommendation is always a single-GPU fit when one exists.
INT4 caveat: requires a quantized checkpoint actually published for this model — check its Hugging Face page before relying on this row.
Cheapest way to run bge-reranker-v2.5-gemma2-lightweight at its published (F32) precision: 1× A40 on runpod, at $0.440/hr per GPU ($0.440/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.
Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
More BAAI models
- bge-reranker-v2-gemma (2.5B, F32)
- Qwen3-0.6B (752M, BF16)
- Qwen3-8B (8.2B, BF16)
- gpt2 (137M, F32)
- Qwen3.5-9B (9.7B, BF16)
- Qwen3.6-35B-A3B-FP8 (36.0B, F8_E4M3)
