The Serving Stack
Start hereCollectionsNewsletter
Sign in

fp16

1 post

NUMBER FORMATS · 02FP16BF16SAME 16 BITS · FP16 STOPS AT 65,504
formatsfp16bf16

FP16 vs. BF16: Same Size, Different Trade

Why training moved from FP16 to BF16, and why a BF16 model may still run fine in FP16: the same 16 bits split differently, measured on Qwen3-8B.

by The Serving Stack

Inference Notes

Once a week: what changed in serving AI models, and what it means if you build, run or pay for them, in about five minutes.

The Serving Stack

Inference Engineering, In Depth

Navigate

HomeStart hereCollectionsNewsletterAll articles

Collections

Inference EnginesHow an LLM Request Becomes TokensLLMs, ExplainedThe GPU for Inference EngineersQuantization in PracticeServing in Production

Links

RSS Feed

Legal

Privacy PolicyTerms of ServiceCookie Policy
© 2026 The Serving Stack. All rights reserved.