What GPU do I need to run BAAI/bge-reranker-v2-gemma?

2.5B parameters, published in F32. View on Hugging Face

2.5B
Parameters
F32
Native precision
GemmaForCausalLM
Architecture
text-classification
Pipeline

bge-reranker-v2-gemma is published by BAAI on Hugging Face, with 313,086 downloads and 87 likes to date. It's a GemmaForCausalLM model built for text-classification, published natively in F32.

VRAM required & cheapest live GPU fit

Required VRAM = weight size at each precision times a flat 1.2 overhead for activations and fragmentation. The KV-cache grows with context and is not in that factor; it is listed per model below where the architecture is published. Full formula and assumptions: methodology.

PrecisionWeight sizeRequired VRAMCheapest live fitGPUs neededEst. $/hr (full fit)
FP329.3 GB11.2 GBV1001$0.110/hr
FP8 (quantized)2.3 GB2.8 GBRTX 5060 Ti1$0.180/hr
INT4 (quantized)1.2 GB1.4 GBRTX 30701$0.088/hr

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 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-gemma at its published (F32) precision: 1× V100, at $0.110/hr per GPU ($0.110/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.

bge-reranker-v2-gemma: KV cache by context length

The KV cache is the memory the attention layers hold for every token of context, on top of the weights. It is not part of the flat 1.2x overhead in the table above, grows with context length and with every concurrent request, and is why a long-context deployment needs more VRAM than the table shows.

Grouped-query attention: every layer caches keys and values for a few shared KV heads. Cached per token: 18,432 bytes at 16-bit.

ContextKV cache, one sequence
4K0.07 GB
8K (model maximum)0.14 GB

Computed from the layer, head and window counts in the model's own configuration (BAAI/bge-reranker-v2-gemma), at 16 bits per cached value. Each concurrent sequence needs its own cache, on top of the weights.

bge-reranker-v2-gemma: common questions

Does bge-reranker-v2-gemma fit on a 12 GB GPU?

Yes. At FP32 it needs 11.2 GB of VRAM, so a 12 GB card holds it with 0.8 GB to spare. An 8 GB card is not enough for it at FP32.

Can bge-reranker-v2-gemma run in 16-bit instead of FP32?

Yes. Its published weights are FP32, 9.3 GB, or 11.2 GB once inference overhead is added. Loading the same weights in 16 bits halves that to 4.7 GB, or 5.6 GB with overhead. That moves it onto a 6 GB card instead of a 12 GB one. How much accuracy the cast costs is model-specific and is not measured here.

What is the least VRAM bge-reranker-v2-gemma can run in?

1.4 GB, at INT4 (quantized), which fits a 6 GB card, against 11.2 GB at FP32. That row assumes an INT4 checkpoint has actually been published for this model, so check its Hugging Face page before planning around it.

Does quantizing bge-reranker-v2-gemma lower the GPU bill?

Yes. At FP32 the cheapest live fit is one V100 at $0.110/hr. At INT4 (quantized) it drops to one RTX 3070 at $0.088/hr, provided a quantized checkpoint exists for it.

Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.

More BAAI models

All 2 BAAI models: VRAM and GPU requirements

More on bge-reranker-v2-gemma

Related reading: V100 pricing and specs, How much VRAM you need for LLMs, and What AI inference is.

Your own GPU cloud accounts

One console for the GPU clouds you already rent from. Your keys stay on your machine.

$20 a month, flat

Connect your accounts

One console for the GPU clouds you already use.

Connect your accounts for $20 a month, flat. Your provider bills the GPU.

© 2026 Aquanode. All rights reserved.

All trademarks, logos and brand names are the property of their respective owners.