FocsleFocsle
Fo’c’sle
Fo’c’sle

Focsle

Reference distillations and the cross-vendor benchmark methodology that powers the platform.

13K followers 8 models Tel Aviv · Cambridge joined Nov 4, 2025
Reference models
4
In Fo’c’sle catalog
Cross-chip benchmarks
25
Across all releases
Downloads (12 mo)
387K
Active deployments
21K

Models

Posts

benchmark report·Apr 18, 2028·12 min read

Cross-chip benchmark report: Q3 2028

Three transformers caught up to YOLO. Hailo-10 dethroned Coral on the low-power tier. Thor justified its watts on VLA. The full numbers, and the surprises.

case study·Apr 9, 2028·9 min read

How Meridian Autonomy compressed chip selection from 14 weeks to 9 days

When the SKU plan calls for four hardware tiers — and your perception stack is six models deep — the chip-selection cycle eats the whole roadmap. Meridian's engineering lead on what changed.

methodology·Mar 28, 2028·14 min read

Inside the HIL lab: methodology for cross-vendor robotics benchmarks

What it means to call a number 'comparable' across silicon vendors — the rig, the harness, the protocol, and the ways we keep ourselves honest.

release·Apr 16, 2028·7 min read

Releasing Depth-Anything-Edge: a 41 MB depth model that runs at 60 FPS on a Pi 5

A distilled monocular depth model with metric-stable outputs, a 0.32 AbsRel on KITTI, and a memory footprint that fits inside the Hailo-8L on a Pi HAT. Weights, recipes, and HIL traces, all open.

platform·Mar 12, 2028·5 min read

Now supporting NVIDIA Jetson Thor and Hailo-10H in HIL Sim

Both platforms are now first-class targets for HIL simulation runs and live in the cross-chip leaderboards. What's new, what's still pending, and how to request runs against your own chip rotation.

opinion·Feb 26, 2028·6 min read

The end of single-vendor edge AI

For two decades, the answer to 'which chip should we build on' was 'whichever one our prior product used'. The next product cycle is going to look different, and not because anyone wants it to.

Contributions to the platform