# Half precision
**URL:** https://discourse.julialang.org/t/half-precision/75580
**Category:** Internals & Design
**Tags:** question
**Created:** [February 1, 2022, 3:38pm UTC](https://discourse.julialang.org/t/half-precision/75580 "2022-02-01T15:38:50Z")
**Posts on this page:** 3
**Page:** 1
### Author:  [@ctkelley](https://discourse.julialang.org/u/ctkelley)
#### Post date: [February 1, 2022, 3:38pm UTC](https://discourse.julialang.org/t/half-precision/75580/1 "2022-02-01T15:38:50Z")
Are there any plans to let people get to the hardware half precision formats (BFloat16 and Float16) in Apple silicon? I have a research interest in mixed precision solvers and would be very excited to stop doing half precision work with only software emulation.
---
### Author:  [@gbaraldi](https://discourse.julialang.org/u/gbaraldi)
#### Post date: [February 1, 2022, 4:01pm UTC](https://discourse.julialang.org/t/half-precision/75580/2 "2022-02-01T16:01:05Z")
The issue to follow for that is [Hardware Float16 on A64fx · Issue #40216 · JuliaLang/julia · GitHub](https://github.com/JuliaLang/julia/issues/40216). Apple silicon for now only has support for Float16 not BFloat16. If you are trying it out I would recommend building julia from source with the lines mentioned in the issue commented out.
---
### Author:  [@ctkelley](https://discourse.julialang.org/u/ctkelley)
#### Post date: [February 1, 2022, 4:15pm UTC](https://discourse.julialang.org/t/half-precision/75580/3 "2022-02-01T16:15:56Z")
Thanks for aiming me at that. I’ve never tried building Juila from source, but the discussion on that issue looks like there’s progress.