正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

#M5StackNew 🎉LLM-8850 Kit (4G) Released LLM-8850 Kit is a high-performance AI accelerator kit designed for edge AI and embedded computing scenarios. It consists of the LLM-8850 Card AI accelerator card, which is based on #Axera AX8850 SoC, and the LLM-8850 PiHat adapter board, enabling the Raspberry Pi platform to... easily integrate high-compute AI acceleration and rapidly build compact, efficient edge intelligence systems. This is 4GB memory version of the LLM-8850 Kit. ✨Features ✅Ultra-compact form factor: M.2 M-Key 2242 size & High-performance NPU: 24 TOPS @ INT8, octa-core Cortex‑A55 1.7 GHz CPU ✅Memory: 4GB 64‑bit LPDDR4x, 4266 Mbps (2+2) ✅Hardware video engine: 8 K @ 30 fps H.264/H.265 encoding, 8 K @ 30 fps decoding, supports 16-channel 1080P parallel decoding ✅Secure boot & encryption: AES / DES / 3DES / SHA‑256 hardware security module ✅Native AXCL: one-click execution of full-stack models including CNN, Transformer, CLIP, Whisper, Llama3.2, Qwen3, InternVL3, etc., supports simultaneous H.264/H.265 encode/decode transcoding 🛒 Get Yours: Shopify: AliExpress: #M5Stack #IoT #M5StackNew #RaspberryPi #Axera #EdgeAI #AIAcceleration #LLM #MachineLearning #Hardware #Makers #EmbeddedSystemsshow more

M5Stack

43,693 subscribers

11,024 次观看 • 12 天前 •via X (Twitter)

#M5StackNew #Axera

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

#M5StackNew 🎉AI Pyramid & AI Pyramid-Pro Released AI Pyramid & AI Pyramid-Pro are pyramid-shaped high-performance AI PCs purpose-built for local AI inference and edge intelligence deployments. Powered by the #Axera AX8850 SoC, they effortlessly handle complex workloads including visual recognition, multimodal interaction, and on‑device large language model inference, compatible with #Immich (AI local photo album), #Frigate (AI smart security), local Home Assistant and #AIGC deployment. ✨Features ✅Axera AX8850 SoC, 24 TOPS @ INT8 ✅4GB (2+2) High‑Bandwidth Memory (8GB for the pro version): 64‑bit LPDDR4x, 4266 Mbps ✅2× HDMI 2.0 digital A/V output ports(1× output + 1× input for the pro version), 4K@60fps supported ✅Hardware Video Engine: 8K @ 30 fps H.264/H.265 encoding & decoding, 16‑channel 1080p parallel decoding supported ✅Native AXCL Support: One‑click deployment for #CNN、#Transformer、#CLIP、#Whisper、#Llama 3.2、#Qwen3、#InternVL3 and other models; H.264/H.265 simultaneous encode/decode/transcode enabled 🛒 Get Yours: 🔹AI Pyramid: Shopify: AliExpress: 🔹AI Pyramid-Pro: Shopify: AliExpress: #M5Stack #M5StackNew #AI #EdgeAI #AIPC #IoT #Hardware #Makers #SmartHome #Axera #Llama3 #DeepLearning

#M5StackNew 🎉AI Pyramid & AI Pyramid-Pro Released AI Pyramid & AI Pyramid-Pro are pyramid-shaped high-performance AI PCs purpose-built for local AI inference and edge intelligence deployments. Powered by the #Axera AX8850 SoC, they effortlessly handle complex workloads including visual recognition, multimodal interaction, and on‑device large language model inference, compatible with #Immich (AI local photo album), #Frigate (AI smart security), local Home Assistant and #AIGC deployment. ✨Features ✅Axera AX8850 SoC, 24 TOPS @ INT8 ✅4GB (2+2) High‑Bandwidth Memory (8GB for the pro version): 64‑bit LPDDR4x, 4266 Mbps ✅2× HDMI 2.0 digital A/V output ports(1× output + 1× input for the pro version), 4K@60fps supported ✅Hardware Video Engine: 8K @ 30 fps H.264/H.265 encoding & decoding, 16‑channel 1080p parallel decoding supported ✅Native AXCL Support: One‑click deployment for #CNN、#Transformer、#CLIP、#Whisper、#Llama 3.2、#Qwen3、#InternVL3 and other models; H.264/H.265 simultaneous encode/decode/transcode enabled 🛒 Get Yours: 🔹AI Pyramid: Shopify: AliExpress: 🔹AI Pyramid-Pro: Shopify: AliExpress: #M5Stack #M5StackNew #AI #EdgeAI #AIPC #IoT #Hardware #Makers #SmartHome #Axera #Llama3 #DeepLearning

M5Stack

21,084 次观看 • 4 个月前

#M5StackNew 🎊 The LLM630 Compute Kit is an #AI large language model (#LLM) inference development kit, powered by the #Axera #AX630C SoC with a 3.2 TOPs NPU, it delivers efficient AI inference for tasks like computer vision (CV) and LLM processing.

#M5StackNew 🎊 The LLM630 Compute Kit is an #AI large language model (#LLM) inference development kit, powered by the #Axera #AX630C SoC with a 3.2 TOPs NPU, it delivers efficient AI inference for tasks like computer vision (CV) and LLM processing.

M5Stack

16,383 次观看 • 1 年前

#M5StackNew 🎉 PaperColor PaperColor is a development board featuring a 4-inch E Ink Spectra 6 full-color e-paper display with a resolution of 400x600, offering both low power consumption and high visibility. ✨Features ✅ESP32-S3R8 Core: 16MB Flash + 8MB PSRAM, 2.4 GHz Wi-Fi ✅ES8311 Audio Codec, 1W Speaker + MEMS Microphone ✅Built-in 1250mAh Battery, microSD Card Slot ✅Infrared Emitter, 2x RGB LED, RX8130CE Real-Time Clock ✅Onboard SHT40 Temperature & Humidity Sensor 🛒 Get Yours: Shopify: AliExpress: #M5Stack #M5StackNew #IoT #PaperColor #ESP32S3 #EInk #EPaper #SmartDisplay #EmbeddedSystems #Makers

#M5StackNew 🎉 PaperColor PaperColor is a development board featuring a 4-inch E Ink Spectra 6 full-color e-paper display with a resolution of 400x600, offering both low power consumption and high visibility. ✨Features ✅ESP32-S3R8 Core: 16MB Flash + 8MB PSRAM, 2.4 GHz Wi-Fi ✅ES8311 Audio Codec, 1W Speaker + MEMS Microphone ✅Built-in 1250mAh Battery, microSD Card Slot ✅Infrared Emitter, 2x RGB LED, RX8130CE Real-Time Clock ✅Onboard SHT40 Temperature & Humidity Sensor 🛒 Get Yours: Shopify: AliExpress: #M5Stack #M5StackNew #IoT #PaperColor #ESP32S3 #EInk #EPaper #SmartDisplay #EmbeddedSystems #Makers

M5Stack

45,351 次观看 • 1 个月前

Introducing MiniCPM 4.1-8B: First Open-Source Reasoning LLM with Trainable Sparse Attention ✅ Strong Reasoning Capability: Surpasses similar-sized models on 15 tasks! ✅ Fast Generation: 3x decoding speedup for reasoning ✅ Efficient Architecture: Trainable sparse attention, frequency-ranked speculative decoding Download Models: Huggingface: Github: Technical Report: #AI #MiniCPM #LLM #OpenBMB #ArtificialIntelligence #MachineLearning

Introducing MiniCPM 4.1-8B: First Open-Source Reasoning LLM with Trainable Sparse Attention ✅ Strong Reasoning Capability: Surpasses similar-sized models on 15 tasks! ✅ Fast Generation: 3x decoding speedup for reasoning ✅ Efficient Architecture: Trainable sparse attention, frequency-ranked speculative decoding Download Models: Huggingface: Github: Technical Report: #AI #MiniCPM #LLM #OpenBMB #ArtificialIntelligence #MachineLearning

OpenBMB

19,236 次观看 • 9 个月前

#M5StackNew 🎉 Unit C6L — a highly‑integrated LoRa communication unit with Stamp C6LoRa module, powered by #Espressif ESP32‑C6 and Semtech Corporation SX1262 LoRa transceiver. ✅ Supports Meshtastic or custom development for private LoRa networks ✅ Supports 868 ~ 923 MHz LoRa & 2.4 GHz Wi‑Fi 6 ✅ Built‑in 0.66" OLED display, programmable RGB LED, buzzer & user button ✅ Integrated overvoltage protection chip for stability 🛒 Get Yours: Shopify: AliExpress: #M5Stack #M5StackNew #LoRa #ESP32C6 #SX1262 #Meshtastic #IoT #Hardware #EdgeConnectivity #Wireless #MakerGear #OutdoorComms #Espressif #Semtech

#M5StackNew 🎉 Unit C6L — a highly‑integrated LoRa communication unit with Stamp C6LoRa module, powered by #Espressif ESP32‑C6 and Semtech Corporation SX1262 LoRa transceiver. ✅ Supports Meshtastic or custom development for private LoRa networks ✅ Supports 868 ~ 923 MHz LoRa & 2.4 GHz Wi‑Fi 6 ✅ Built‑in 0.66" OLED display, programmable RGB LED, buzzer & user button ✅ Integrated overvoltage protection chip for stability 🛒 Get Yours: Shopify: AliExpress: #M5Stack #M5StackNew #LoRa #ESP32C6 #SX1262 #Meshtastic #IoT #Hardware #EdgeConnectivity #Wireless #MakerGear #OutdoorComms #Espressif #Semtech

M5Stack

14,071 次观看 • 8 个月前

#M5StackNew 🎉 StopWatch StopWatch is a portable AMOLED round touch development board designed for interactive and wearable scenarios, integrating display, touch, audio and motion sensing into one compact device. ✨Features ✅ ESP32-S3R8 core controller with 16MB Flash, 8MB PSRAM, and 2.4GHz Wi-Fi ✅ 1.75" AMOLED Touch Round Display, 2 x Programmable Buttons, 1 x Power Button ✅ Built-in Vibration Motor, 6-axis IMU BMI270, RX8130CE RTC ✅ ES8311 Audio Codec, MEMS MIC, AW8737A Amplifier for audio input and output ✅ HY2.0-4P Expansion Interface, M5PM1 Multi-level Power Management System, Built-in 450mAh Battery 🛒 Get Yours: Shopify: AliExpress: #M5Stack #M5StackNew #IoT #ESP32S3 #AMOLED #WearableTech #Embedded #HMI #TouchDisplay #SmartDevices

#M5StackNew 🎉 StopWatch StopWatch is a portable AMOLED round touch development board designed for interactive and wearable scenarios, integrating display, touch, audio and motion sensing into one compact device. ✨Features ✅ ESP32-S3R8 core controller with 16MB Flash, 8MB PSRAM, and 2.4GHz Wi-Fi ✅ 1.75" AMOLED Touch Round Display, 2 x Programmable Buttons, 1 x Power Button ✅ Built-in Vibration Motor, 6-axis IMU BMI270, RX8130CE RTC ✅ ES8311 Audio Codec, MEMS MIC, AW8737A Amplifier for audio input and output ✅ HY2.0-4P Expansion Interface, M5PM1 Multi-level Power Management System, Built-in 450mAh Battery 🛒 Get Yours: Shopify: AliExpress: #M5Stack #M5StackNew #IoT #ESP32S3 #AMOLED #WearableTech #Embedded #HMI #TouchDisplay #SmartDevices

M5Stack

35,710 次观看 • 1 个月前

🎉 StackChan Quick Start StackChan is a super kawaii AI desktop robot co-created by M5Stack and the user community. It uses the M5Stack CoreS3 as its main controller, powered by an ESP32-S3 SoC featuring a 240 MHz dual-core processor, with 16MB Flash and 8MB PSRAM onboard, and supporting Wi-Fi and BLE. ✨Features ✅Based on the CoreS3 main unit ✅USB-C interface for power and data, 550 mAh battery ✅Two feedback servos (360-degree continuous rotation on the horizontal axis and 90-degree movement on the vertical axis) ✅Two rows totaling 12 RGB LEDs, Full-featured NFC ✅Infrared transmitter and receiver, Top-mounted three-zone touch panel * StackChan Remote Controller Kit has an additional remote controller (assembled from a Hat Mini JoyC and StickC-Plus) compared to StackChan. 🛒 Get Yours: Shopify: StackChan: StackChan Remote Controller Kit: AliExpress: #M5Stack #M5StackNew #StackChan #IoT #DesktopRobot #ESP32 #Makers #SmartDevice

🎉 StackChan Quick Start StackChan is a super kawaii AI desktop robot co-created by M5Stack and the user community. It uses the M5Stack CoreS3 as its main controller, powered by an ESP32-S3 SoC featuring a 240 MHz dual-core processor, with 16MB Flash and 8MB PSRAM onboard, and supporting Wi-Fi and BLE. ✨Features ✅Based on the CoreS3 main unit ✅USB-C interface for power and data, 550 mAh battery ✅Two feedback servos (360-degree continuous rotation on the horizontal axis and 90-degree movement on the vertical axis) ✅Two rows totaling 12 RGB LEDs, Full-featured NFC ✅Infrared transmitter and receiver, Top-mounted three-zone touch panel * StackChan Remote Controller Kit has an additional remote controller (assembled from a Hat Mini JoyC and StickC-Plus) compared to StackChan. 🛒 Get Yours: Shopify: StackChan: StackChan Remote Controller Kit: AliExpress: #M5Stack #M5StackNew #StackChan #IoT #DesktopRobot #ESP32 #Makers #SmartDevice

M5Stack

55,394 次观看 • 1 个月前

The ultimate local AI developer platform is here. AMD Ryzen AI Halo presale is now live! Built for #AMDevs, Ryzen AI Halo delivers the performance, memory, and AI capabilities needed to build, test, and run agentic AI, generative AI, LLM applications, and more locally. Reserve yours now:

The ultimate local AI developer platform is here. AMD Ryzen AI Halo presale is now live! Built for #AMDevs, Ryzen AI Halo delivers the performance, memory, and AI capabilities needed to build, test, and run agentic AI, generative AI, LLM applications, and more locally. Reserve yours now:

AI at AMD

19,309 次观看 • 15 天前

I sent an AI computer to the edge of space! HAAID-1 was the first-of-its-kind high-altitude balloon mission. It reached an altitude of ~19 km and ran a 360M-parameter LLM on a Raspberry Pi at -68°C.

I sent an AI computer to the edge of space! HAAID-1 was the first-of-its-kind high-altitude balloon mission. It reached an altitude of ~19 km and ran a 360M-parameter LLM on a Raspberry Pi at -68°C.

Yatharth Mann

108,594 次观看 • 19 天前

Decentralized AI ✅ Testnets ✅ Mainnet Imminent ✅ Full Privacy ✅ Fully Homomorphic Encryption ✅ zk-LLM ✅ Cerberus Squeezing ✅ dApp/Smart Contracts ✅ @kyle_chasse ✅

Decentralized AI ✅ Testnets ✅ Mainnet Imminent ✅ Full Privacy ✅ Fully Homomorphic Encryption ✅ zk-LLM ✅ Cerberus Squeezing ✅ dApp/Smart Contracts ✅ @kyle_chasse ✅

BasedAI

29,017 次观看 • 1 年前

🚀 AI at the Edge with #Ubuntu & Renesas Electronics! At Embedded World 2025, we demonstrated how Ubuntu enables secure, scalable, and high-performance edge AI solutions. With Secure Boot, full disk encryption, and inference running directly on a CPU in kiosk mode, this setup showcases the future of embedded intelligence. Watch the demo in action! How do you see AI at the edge transforming industries? #Ubuntu #Renesas #ew25 #embeddedworld #IoT #EdgeAI

🚀 AI at the Edge with #Ubuntu & Renesas Electronics! At Embedded World 2025, we demonstrated how Ubuntu enables secure, scalable, and high-performance edge AI solutions. With Secure Boot, full disk encryption, and inference running directly on a CPU in kiosk mode, this setup showcases the future of embedded intelligence. Watch the demo in action! How do you see AI at the edge transforming industries? #Ubuntu #Renesas #ew25 #embeddedworld #IoT #EdgeAI

Ubuntu

13,694 次观看 • 1 年前

🧠 Dell is rethinking what enterprise AI can do — and where it lives. At Dell Tech World, Sam Grocott shared how Dell Technologies is deploying Glean’s Work AI Platform on-prem — blending public LLM intelligence with private infrastructure to power sensitive, high-trust use cases. The result? AI that acts on your behalf to: ✅ Write emails ✅ Prep meetings ✅ Push deals forward — autonomously This is Dell’s vision for agentic AI: a 24/7 teammate driving go-to-market productivity to new heights — securely, efficiently, and always on. Get the full story:

🧠 Dell is rethinking what enterprise AI can do — and where it lives. At Dell Tech World, Sam Grocott shared how Dell Technologies is deploying Glean’s Work AI Platform on-prem — blending public LLM intelligence with private infrastructure to power sensitive, high-trust use cases. The result? AI that acts on your behalf to: ✅ Write emails ✅ Prep meetings ✅ Push deals forward — autonomously This is Dell’s vision for agentic AI: a 24/7 teammate driving go-to-market productivity to new heights — securely, efficiently, and always on. Get the full story:

Six Five Media

92,894 次观看 • 11 个月前

👨🏻‍💻 LLM Engineer Toolkit - Collection of 120+ LLM Libraries Category Wise LLM Engineer Toolkit repository contains a curated list of 120+ LLM libraries category wise. 🚀 LLM Training 🧱 LLM Application Development 🩸LLM RAG 🟩 LLM Inference 🚧 LLM Serving 📤 LLM Data Extraction 🌠 LLM Data Generation 💎 LLM Agents ⚖️ LLM Evaluation 🔍 LLM Monitoring 📅 LLM Prompts 📝 LLM Structured Outputs 🛑 LLM Safety and Security 💠 LLM Embedding Models ❇️ Others Repo -

👨🏻‍💻 LLM Engineer Toolkit - Collection of 120+ LLM Libraries Category Wise LLM Engineer Toolkit repository contains a curated list of 120+ LLM libraries category wise. 🚀 LLM Training 🧱 LLM Application Development 🩸LLM RAG 🟩 LLM Inference 🚧 LLM Serving 📤 LLM Data Extraction 🌠 LLM Data Generation 💎 LLM Agents ⚖️ LLM Evaluation 🔍 LLM Monitoring 📅 LLM Prompts 📝 LLM Structured Outputs 🛑 LLM Safety and Security 💠 LLM Embedding Models ❇️ Others Repo -

Kalyan KS

16,643 次观看 • 1 年前

Reminder: Earlier this week, we launched "Getting Structured LLM Output," in collaboration with .txt. In this course, you'll: ✅ Get an overview of structured output generation, its importance, and the different approaches to generating them. ✅ Build a social media agent using structured output and learn how to use re-prompting libraries like 'instructor.' ✅ Understand the concepts behind constrained decoding and how the LLM logits are modified to get a particular output structure. Learn for free:

Reminder: Earlier this week, we launched "Getting Structured LLM Output," in collaboration with .txt. In this course, you'll: ✅ Get an overview of structured output generation, its importance, and the different approaches to generating them. ✅ Build a social media agent using structured output and learn how to use re-prompting libraries like 'instructor.' ✅ Understand the concepts behind constrained decoding and how the LLM logits are modified to get a particular output structure. Learn for free:

DeepLearning.AI

17,313 次观看 • 1 年前

Another example of the multiple TTS parallel pipelines pattern. Here's a voice AI agent that speaks both English and Arabic, using a specific model/voice for each language. These are PlayAI voices. The STT, TTS, and LLM inference is all running on Groq Inc. (The LLM is LLama 4 Maverick.)

Another example of the multiple TTS parallel pipelines pattern. Here's a voice AI agent that speaks both English and Arabic, using a specific model/voice for each language. These are PlayAI voices. The STT, TTS, and LLM inference is all running on Groq Inc. (The LLM is LLama 4 Maverick.)

kwindla

13,328 次观看 • 1 年前

Nintendo Switch 2 chip is a technical marvel and bring together several breakthroughs ✅ The most advanced graphics ever in a mobile device ✅ Full hardware ray tracing ✅ High dynamic range ✅ Backwards compatibility architecture ✅ Dedicated AI processors to improve gameplay

Nintendo Switch 2 chip is a technical marvel and bring together several breakthroughs ✅ The most advanced graphics ever in a mobile device ✅ Full hardware ray tracing ✅ High dynamic range ✅ Backwards compatibility architecture ✅ Dedicated AI processors to improve gameplay

Croc Oclock

28,003 次观看 • 1 年前

Download the latest ChatRTX update for new features: ✅ More LLM Models ✅ Image Search ✅ Voice Support Learn more in this week's #AIDecoded blog 👉

Download the latest ChatRTX update for new features: ✅ More LLM Models ✅ Image Search ✅ Voice Support Learn more in this week's #AIDecoded blog 👉

NVIDIA GeForce

98,671 次观看 • 2 年前

🔥 Major Upgrade 🔥 Node Sphere AI + ChainGPT Web3 LLM = 🚀 On-chain agents now think in real-time: ✅ Live token & wallet data ✅ DeFi + NFT insights ✅ Gas & smart contract parsing AI is finally Web3-native.

🔥 Major Upgrade 🔥 Node Sphere AI + ChainGPT Web3 LLM = 🚀 On-chain agents now think in real-time: ✅ Live token & wallet data ✅ DeFi + NFT insights ✅ Gas & smart contract parsing AI is finally Web3-native.

Node Sphere AI

13,519 次观看 • 11 个月前

Yann LeCun says the AI industry is completely LLM pilled.

Yann LeCun says the AI industry is completely LLM pilled.

hinata

56,027 次观看 • 2 个月前

INTRODUCING Notte Building the agentic internet with the strongest web browser for LLM agents. We transform ANY webpage into structured text, enabling better web understanding and navigation. Plug any LLM to to build your own AI agent

INTRODUCING Notte Building the agentic internet with the strongest web browser for LLM agents. We transform ANY webpage into structured text, enabling better web understanding and navigation. Plug any LLM to to build your own AI agent

Notte

225,195 次观看 • 1 年前