Taskaya: Custom ASICs do not make sense given low Nvidia GEMM overhead
Batuhan Taskaya · A Technical History of Generative Media · Sep 8, 2025 · at 25:25
Batuhan Taskaya, co-founder of Fal, explains to podcast host Swix why developing custom ASICs for diffusion and AI workloads is economically unviable compared to Nvidia GPUs.
0:00 / 0:10exact quote · 10.5s
▶ Watch the full episode on YouTube → 720p mp4 · rendered on demand · StarZero watermark
“What is the overhead of an NVIDIA GAM instruction, right? It's like 16%. So like you're essentially buying a, Matrix multiplication machine. So, like, it doesn't really make sense to specialize it that much.”
quote is from the automated transcript, cleaned for reading: filler sounds and stutters are removed, nothing is rephrased. names can be misheard (the analysis reads context, assessments check outside sources). how →
More from Batuhan Taskaya
Taskaya: Flux was the first enterprise-ready generative image model
“The team at Stability left to start Black Forest Labs, which released Flux models. And that was the first model to, you know, breach the barrier of commercially usable, you know, enterprise-ready grade models”
Taskaya: NSFW content makes up less than 1% of Fal traffic
“Moderation is optional to a level where, like, illegal content is moderated, and we also track, like, the non-illegal content NSFW moderation, and, like, we haven't seen, like, we haven't seen more than one percent.”
Taskaya: 80% of promotional video content will be AI-generated within 12 months
“Like 12 months, I think like 80% of this is going to be generated.”
Taskaya: Training a state-of-the-art image model costs under $1M
“Like right now, like if you look, if you want to train a Sota image model, I don't think it's going to cost more than a million dollars. It's extremely cheap. It's like a matter of data engineering effort, cleaning. It's, I think it's a function of data set.”