<!--
{
  "availability" : [
    "iOS: 27.0.0 -",
    "iPadOS: 27.0.0 -",
    "tvOS: 27.0.0 -",
    "visionOS: 27.0.0 -",
    "watchOS: 27.0.0 -"
  ],
  "documentType" : "symbol",
  "framework" : "CoreAI",
  "identifier" : "/documentation/CoreAI/NDArray/ScalarType-swift.enum/bfloat16",
  "metadataVersion" : "0.1.0",
  "role" : "Case",
  "symbol" : {
    "kind" : "Case",
    "modules" : [
      "Core AI"
    ],
    "preciseIdentifier" : "s:13CoreAIRuntime7NDArrayV10ScalarTypeO8bfloat16yA2EmF"
  },
  "title" : "NDArray.ScalarType.bfloat16"
}
-->

# NDArray.ScalarType.bfloat16

A 16-bit brain floating-point type.

```
case bfloat16
```

## Discussion

BFloat16 (Brain Floating Point) uses 8 exponent bits and 7 mantissa bits, matching the
exponent range of Float32 but with reduced precision. This type is widely supported across
most operations including matrix multiplication, activation functions, and quantization.

---

Copyright &copy; 2026 Apple Inc. All rights reserved. | [Terms of Use](https://www.apple.com/legal/internet-services/terms/site.html) | [Privacy Policy](https://www.apple.com/privacy/privacy-policy)