Replies: 2 comments
-
|
FYI, Axera representative has started a Frigate NVR discussion here:
Fork of Frigate with initial Axera support: AXERA-TECH rep also mentioned these Huggingface models: |
Beta Was this translation helpful? Give feedback.
-
|
FYI, also see the "Radxa AICore AX-M1" M.2 2280 M Key form-factor AI Acceleration Module (M72T) is based the same Axera AX8850 SoC: Radxa has not yet posted anything about pricing or when it will be availability. Radxa officially lists the ROCK 5A, 5B, 5B+, and ROCK 5 ITX boards as tested. 
Note! While not 100% sure I believe Axera AX8850 is the same as the Axera M76H SoC on their site targeting "smart driving"(?): RapidAnalysis posted a demo-video of a preview unit from Radxa that looks like a final protoype that has "radxa AICore M72T V1.0" printed on it. Video show simple demo of DeepSeek-R1-Qwen-7B and SmolLM2-360M-Instruct large language model(s): Radxa has a support listing for Large Language Models, small and large Vision models, Speech Models, Text-to-image Generation models: Large Language Models:
Vision Large Models:
Speech Models:
Text-to-image Generation Model:
Vision Model:
|
Beta Was this translation helpful? Give feedback.
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
-
M5Stack LLM-8850 is a new M.2 M-Key (2242 NGFF socket) AI accelerator card for $99! Based on Axera AX8850 24 TOPS @ INT8 NPU SoC:
Wondering if we could get support for this by default in Frigate NVR add-on under the official Home Assistant Operating System distro?
This is a new LLM8850 M.2 AI accelerator module is less expensive alternative than competes with the Hailo-8 based the Raspberry Pi AI Kit (same as Hailo-8L M.2 AI Accelerator) and Waveshare Hailo-8 M.2 AI Accelerator Module (same as Hailo-8 M.2 AI Accelerator), and just like those this too is designed primarly for "Edge AI" on single-board-computers such as Raspberry Pi 5 / CM5, Rockchip RK3588 SBCs (like example NanoPC-T6, NanoPi R6C, Orange Pi 5 Plus, Banana Pi BPI-M7), and small-form-factor x86-64 Mini-PCs (like Intel NUC series) with a spare M.2 Key-M socket.
M5Stack guide say they tested it in Raspberry Pi environment setup using the official M.2 HAT+ on a Raspberry Pi 5:
On paper the Axera 8850 SoC Edge NPU coprocessor is howerver far superior on general AI acceleration / AI generation and thus more flexible then the Hailo-8 M.2 cards which in turn are more or less optimized for computer vision applications.
The M5Stack LLM-8850 card supports PCIe 2.0 ×2 lanes and onboard it has 8GB RAM (64 bit LPDDR4x @ 4266 Mbps) which NPU capable of up to 24 TOPS @ INT8 (based on Axera AX8850 Octa-Core Cortex‑A55 1.7 GHz CPU SoC). It also supports H.265/H.264 8Kp30 video encoding and 8Kp60 video decoding, with up to 16 channels for 1080p videos, so another use case would be on-the-fly video transcoding acceleration for Frigate NVR, other than real-time AI object detection (similar to the Google Coral TPU M.2 Accelerator Edge TPU coprocessor. The main downside (other than it only having 8GB of VRAM) is that M5Stack LLM-8850 card runs a hotter so need a fan for active cooling as maximum load it uses 7W @ 3.3V and runs at 70 °C degrees (so it probably get way too hot to run inside the Home Assistant Yellow enclosure).
https://www.youtube.com/watch?v=zBlaAHn4aF8
M5Stack sells the Axera AX8850 M.2 module for $99 US-dollar in its own online store (and on its on AliExpress store):
PS: M5Stack is a subsidiary of Espressif (of ESP32/ESP8266 fame):
Beta Was this translation helpful? Give feedback.
All reactions