Model Releases
just ran this on my phone (17 pro)
just ran this on my phone (17 pro) Every on-device AI benchmark you've seen was measured on someone else's phone. So we stopped posting numbers and shipped the benchmark instead. Built into the RunAny
just ran this on my phone (17 pro) Every on-device AI benchmark you've seen was measured on someone else's phone. So we stopped posting numbers and shipped the benchmark instead. Built into the RunAnywhere app: pick any model, hit Run, and it measures performance on your device. → Tokens/sec + time-to-first-token …
Related
- ran my first benchmark this weekend (longmemeval) mostly to test activegraph, learned a lot! - this is a stepping stone to show the event ba…
- this is even easier
- even though @activegraphai is not a memory tool, it's a runtime built around memory so it can do well there cool to see a third party verify…
- oh even better, since you can test the runtime without an LLM, you can post this into Claude: “look up http://activegraph.ai, install and ru…
Source: Yohei Nakajima (X) | 2026-07-15