Home/Models/Bert Base Uncased
Google logo

Bert Base Uncased

by Google · Released Mar 2022

Open Source
Compare
Context
N/A
Input $/1M
n/a
Output $/1M
n/a
Type
fill-mask
License
Open Source
Benchmarks
0 tested
Data as of
About

Google-bert fill mask model. 72047K downloads on HuggingFace.

No benchmark data available yet.

Links
Documentation
Community
BenchGecko API
google-bert-bert-base-uncased
Specifications
  • Typefill-mask
  • ContextN/A
  • ReleasedMar 2022
  • LicenseOpen Source
  • StatusActive
Available On
Google logoGooglen/a
Share & Export
Tweet
Bert Base Uncased is an open-source fill-mask AI model by Google, released in March 2022.

Identifiers and sizes

  • Hugging Face repo · google-bert/bert-base-uncased
  • License · apache-2.0
  • Total parameters · 110M (110,106,428) · source Hugging Face safetensors · fetched 2026-11-14
  • Weights as published · 0.4 GB in F32 (computed from the safetensors tensor counts per dtype)
  • Weights size, computed · 0.2 GB at BF16/FP16 · 0.1 GB at INT8/Q8 · 0.1 GB at Q4 (computed from the parameter count, not measured; excludes KV cache and runtime overhead)

Key facts · as of 2026-04-09

  • Bert Base Uncased by Google. Not enough public benchmark scores to rank yet.
  • List price n/a input · n/a output per 1M tokens (as of 2026-04-09).

How to cite · data as of 2026-04-09

Bert Base Uncased · benchmarks, pricing and providers. BenchGecko, data as of 2026-04-09. https://benchgecko.ai/model/google-bert-bert-base-uncased

Credit "Source: BenchGecko" with a link. Prices per provider and Gecko Tests are BenchGecko data (CC BY 4.0); benchmark scores keep their original source, listed in the JSON. JSON · llms.txt · MCP