Mythic's analog compute-in-memory chip delivers 100x energy efficiency for AI
Mythic's analog compute-in-memory architecture
Mythic's analog compute-in-memory architecture stores AI model weights in flash memory and computes directly at the source, eliminating the energy waste of shuttling data between processor and memory. The APU (Analog Processing Unit) achieves 100x greater efficiency than GPUs, validated by Honda and the U.S. Department of Defense. Products include the M1 for edge applications and the upcoming M2 chiplet platform for enterprise LLMs. With the acquisition of Videantis, Mythic's ADAS platform is already in 30 million vehicles.
We store AI model weights inside flash memory and compute in analog, directly at the source, eliminating the waste at its origin.
- mdp2021
> Mythic M1 stores up to 80 million neural network weight parameters directly on-chip
Which means connecting over 30 chiplets to run a Qwen 3.8 27b and over 3000 chiplets to run Qwen3.8-2.4T-A95B. Cost? Space? Feasibility?
- phdelightful
My understanding (perhaps outdated) is that manufacturing variability is a key challenge for analog computing. Digital designs are also fundamentally analogue under the hood, but if you only need to resolve a 0 or 1 you are much more tolerant of any source of noise. I wouldn't mind hearing even a little bit more from Mythic about how they make this work in practice.
A 2026 EE Times article [1] refers to "compensation" and "calibration" techniques.
[1] https://www.eetimes.com/mythic-rises-from-the-ashes-with-125...
- tancop
Their numbers look too good to be true, they have no identified customers and the whole site is generated, but I think the principle behind it is good. If they can pull off the error correction needed to make analog reliable we might have a great new option for cheaper more eco friendly AI. Then again it could turn out to be a total scam.