aegis_camera

It's a subset task. ..

When you are not at home, you can send your message to your dashboard agent for your query. This is one use case I found.

You are right. I have Mac mini M2 16GB, it does hold all the cameras I have. Small models like QWEN 9B + LFM 450M handle their security job nicely with < $400 budge.

Will extend the test to more model and thanks again for your insight.

:)

Thanks a lot for your feedback :) I've noticed the slow down of QWEN3.5, so I turned it off thinking mode, the thinking mode even count words like ( 1 count 2 the 3 words, lol which is very funny ).

You are very correct, I just have 2 days of the MBP PRO 64GB on hands, so the test is just covering LLM part -- the logic handling.

For VLM, LFM is the best, even 450M works, I'll update soon :) Thanks again for your deep understanding of LLM/VLM domain and your suggestion.

Thanks for your insight, hardware of AI will be cheaper and memory of footage would be always saved locally.

Thanks for pointing out Unifi Protect, as long as the camera supports ONVIF(RTSP), then it could be connected, please let me know more, I'm not familiar with Unifi Protect, will do more research...

Aegis is able to connect to ONVIF camera, save motion triggered clips. Apply VLM pipeline for context understanding.

It also helps to download video clips from BLINK/RING cameras, so you have persistent memory of all your video clips locally.

This a good platform. I was thinking about to get one

I have also 4070 laptop version during heavy discount season, before 50series came. And upgrade to 96GB DDR5 when it's cheap... So I like LFM 450M + QWEN 9B Q4, they are good fit to 8GB VRAM.

Exactly, the memory of full context is very personal, so I'd like to keep the local.

LFM 450M for vision task, QWEN 9B Q4 for Orchestration, this provides a good result.

My prefer is LFM 450M for vision task, QWEN 9B Q4 for Orchestration

Entry level is actually MAC MINI 16GB at <$499, I have models running on M2 MINI 16GB, it's working with small models.

Will also test DGX SPARK which I have.

Memory is the limitation, M5 has larger memory options. So large language model could be used.

The M5 Pro just dropped, so here's a real AI workload instead of another Geekbench score. We run Qwen3.5 as the brain of a fully local home security system and benchmarked it against OpenAI cloud models on a custom 96-test suite. The Qwen3.5-9B scores 93.8% — within 4 points of GPT-5.4 — while running entirely on the M5 Pro at 25 tok/s, 765ms TTFT, using only 13.8 GB of unified memory. The 35B MoE variant hits 42 tok/s with a 435ms TTFT — faster first-token than any OpenAI cloud endpoint we tested. Zero API costs, full data privacy, all local. Full results: https://www.sharpai.org/benchmark/