AI & Agents
Cactus Compute
Last updated 2026-08-12 · benchmark measured 2026-08-12 — deterministic & reproducible
Needle 2 is a 14MB language model built for tool calling on low-cost edge devices.
Is Cactus Compute production-ready?
Legit.Show scores Cactus Compute 70 out of 100 — the simple average of its 7 measured frames. Legit.Show ran its deterministic 7-Frame production-readiness benchmark on Cactus Compute (public-surface assessment), measured from the public surface with no LLM in the scoring path. Its strongest frame is Reliability; its weakest is Privacy. Every frame it averages is published with its evidence on the Legit.Show listing.
The 7 Frames
- Performance — 59/100
- Accessibility — 98/100
- Security — 45/100
- Privacy — 0/100
- Reliability — 100/100
- Standards — 89/100
- Discoverability — 100/100
What we measured
- Security headers present: HSTS.
- No Content-Security-Policy.
- Served over HTTPS with a valid certificate.
- Real Lighthouse performance run — 395 ms to first byte.
- Returns a proper 404 for unknown routes.
- 3 of 3 sampled routes reachable.
- No privacy policy found.
- Sets cookies / loads scripts with no consent prompt.
Who built it
product account @cactuscompute
Who it's for
IoT developers · Edge AI engineers · Smart home builders · Robotics developers · Mobile device manufacturers
Visit Cactus Compute → · Alternatives to Cactus Compute → · How this was measured →