What GPU do I need to run google-bert/bert-base-uncased?
110M parameters, published in F32. View on Hugging Face
Set up bert-base-uncasedbert-base-uncased is published by google-bert on Hugging Face, with 63,694,017 downloads and 2,842 likes to date. It's a BertForMaskedLM model built for fill-mask, 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.
| Precision | Weight size | Required VRAM | Cheapest live fit | GPUs needed | Est. $/hr (full fit) |
|---|---|---|---|---|---|
| FP32 | 0.4 GB | 0.5 GB | Quadro M4000 | 1 | $0.058/hr |
| FP8 (quantized) | 0.1 GB | 0.1 GB | RTX 5060 Ti | 1 | $0.110/hr |
| INT4 (quantized) | 0.1 GB | 0.1 GB | RTX 5060 Ti | 1 | $0.110/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 bert-base-uncased at its published (F32) precision: 1× Quadro M4000, at $0.058/hr per GPU ($0.058/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.
bert-base-uncased: common questions
How much VRAM does bert-base-uncased need?
0.5 GB at FP32, 0.1 GB at FP8 (quantized), 0.1 GB at INT4 (quantized). All of those sit under 6 GB, the smallest capacity this page reasons about, so VRAM is not what limits where this model runs. The 0.4 GB of weights plus inference overhead is the whole requirement.
Can bert-base-uncased run in 16-bit instead of FP32?
Yes. Its published weights are FP32, 0.4 GB, or 0.5 GB once inference overhead is added. Loading the same weights in 16 bits halves that to 0.2 GB, or 0.2 GB with overhead. How much accuracy the cast costs is model-specific and is not measured here.
How many copies of bert-base-uncased fit on one Quadro M4000?
16, by VRAM alone. That card carries 8.0 GB and one copy needs 0.5 GB at FP32, on a live rate of $0.058/hr for the whole card. Throughput is not modelled here, so 16 copies is not 16 times the requests served.
Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
More on bert-base-uncased
Fits on an 8 GB GPU at FP32: every model that fits in 8 GB.
Related reading: H100 pricing and specs, How much VRAM you need for LLMs, and What AI inference is.
