yeah, it appears to support audio and image input.. and runs on mobile devices with 256K context window!

The E2B and E4B models support 128k context, not 256k, and even with the 128k... it could take a long time to process that much context on most phones, even with the processor running full tilt. It's hard to say without benchmarks, but 128k supported isn't the same as 128k practical. It will be interesting to see.