4. MXFP4, FP4, FP8
Frontier AI Drawings by Hand ✍️
When OpenAI released gpt-oss, I noticed something small but important buried in their model card:
“… quantization of the MoE weights to MXFP4 format …”
Almost right away, a leading AI company working on local inference reached out:
“Our AI engineers need to understand MXFP4 …. they need to understand how it fits 120 billion parameters into 80GB GPU memory.”
Lesser-known players have experimented with MXFP4 in various parts of their pipelines. But seeing OpenAI adopt it in gpt-oss tells us this isn’t just a niche trick anymore.
The idea behind MXFP4 is simple — but it’s not explained well in materials you can find online elsewhere. Existing materials are either papers with hard-to-understand equations or articles listing CUDA kernel code. And explaining it in a way where you can actually calculate it by hand ✍️ — that’s the hard part.
Drawings
For this Issue, I created four new drawings:
FP8-E4M3
FP8-E5M2
FP4-E2M1
MXFP4
Download
The Frontier AI drawings are available to AI by Hand Academy members. You can become a member via a paid Substack subscription.