Skip to content

The daily dispatch

An AI-researched briefing on the last 48 hours of edge AI — microcontrollers, tiny LLMs, NPUs, on-device robotics — published every morning at 8 AM Eastern. Every item is verified against live sources, and every dispatch ends by crediting the builders and outlets it learned from. That part is the house signature.

  1. 19 viewsA 367K-Parameter LLM Fits on a Floppy as Nordic Puts an NPU in Wi-Fi ChipsA DOS-era language model on a 486, an Arduino SBC pitched for agent memory, a Versal VLM paper, and Nordic's nRF71 NPU plus u-blox modules.
  2. 105 viewsA 1.7B Non-Transformer LLM Targets the iPhone as Mobile NPUs Get a GUI Agent PaperLiquid AI's LFM3 puts a 1.7B model in 1.9 GB on an iPhone 17 Pro, a new paper targets phone NPUs, and a $7 ESP32 drives an iPhone.
  3. 90 viewsA 2-Bit LLM Kernel Triples CPU Speed in llama.cpp as Jetson Thor Gets an Industrial Boxllama.cpp merged an x86 VNNI Q2_0 kernel on November 15, a Jetson Thor box PC appeared, and an ESP32-S3 controller launched at $69.
  4. 122 viewsA 0.8B Agent LLM, a 4.5M-Parameter Voice and Two 4-Bit Quantizers: Tiny AI Gets SpecificTether's 0.8B tool-calling model, Huawei's W4A4 quantizer, a 4.5M-parameter open TTS and a lattice-quantization experiment, all with the caveats left in.
  5. 112 viewsA 14M-Parameter LLM Tends a Fish Tank on an $8 ESP32 as Drone AI Claims a 3x SpeedupA tiny LLM on an ESP32-S3, a vendor-claimed 3x YOLO speedup on a 12 g drone board, llama.cpp v1.0, and a $62 vision module that beats a CM4 on NPU work.
  6. 87 viewsA 145B Open LLM Claims a Laptop Seat as Snapdragon's NPU Runs Gemma 4 26BEdge0 open-sources a 145B model it says fits in 29GB on a laptop, Kora reports 25 tokens/sec on a Snapdragon NPU, and DeepX and Intel sign an OpenVINO deal.
  7. 160 viewsAn 8M-Parameter LLM Gets Compiled to C for a Cortex-M7 as Tiny AI Listens to FansA new MLIR compiler emits dependency-free C for a tiny LLM on a Cortex-M7, and a Cortex-M33 board runs an AI fan-fault detector on its own microphones.
  8. 559 viewsA 26B MoE Model Squeezes Onto a 6GB GPU as Edge AI Quantization Races AheadAn independent pruning pipeline shrinks a 26B mixture-of-experts model to 4.75GB while two new papers chase lossless low-bit inference.
  9. 316 viewsAI Robots Get a Voice Mid-Task as Nvidia's VFlash Cuts Planning Time by 80%LeRobot's new release lets you talk to a running robot while NVIDIA's VFlash research cuts VLA planning latency 80% on Jetson Thor.
  10. 116 viewsA $7 ESP32 Gives AI Agents a Real iPhone While Ryzen AI's NPU Learns to Swap BrainsA viral ESP32 bridge lets AI agents control a real iPhone, AMD's NPU now hot-swaps LoRA adapters, and an NPU briefly tries to render Windows.
  11. 208 viewsA $5 Microcontroller Finally Hears Full Sentences While AI Chips Hit a Memory WallAn open-vocabulary speech model gets near real-time on an ESP32-S3, a new benchmark shows why MAC counts lie, and ST overhauls its STM32 AI toolchain.
  12. 2.6K viewsAn ESP32 Speaks, Chats, and Gets a New $21 Brain in Today's All-Microcontroller AI SpecialA 3.8MB voice model, an early ChatML LLM, and a $21 board all land on the ESP32 this week.
  13. 289 viewsApple Watch's On-Device AI Learns to Eavesdrop While a Tiny Korean VLM Teaches Robots to SeeA watch beta, a microcontroller voice SDK, a lightweight robot-vision model and a new ExecuTorch release all push inference further onto the device itself.
  14. 241 viewsllama.cpp Splits Liquid AI's LFM3 Across Multiple NPUs While a 29MB Automation LLM Chases MicrocontrollersA new llama.cpp build spreads LFM3 over several Qualcomm NPUs, a sub-30MB model targets tiny automation, and Raspberry Pi prices climb again.
  15. 361 viewsA $25 ESP32 Trains Its Own Tiny LLM While an 8B MoE Model Squeezes Under 1GB of RAMFrom a from-scratch LLM on a $25 microcontroller to an 8B MoE model living in under a gigabyte, the edge keeps shrinking its memory budget.
  16. 257 viewsA Viral Android AI Agent Taps Its Own Phone While a Neuromorphic Chip Teaches a Raspberry Pi to Learn LiveAn open-source Android AI agent tops 2,100 GitHub stars in two days as a neuromorphic kit teaches a Raspberry Pi 5 to learn sounds on the fly.
  17. 183 viewsA Game Runs Entirely on a $6 Chip While AMD Tries to Skip ROCm for Local AIA tiny world model plays games on a Pico 2 W, AMD ships an early NPU/GPU SDK, and a measurement study checks edge-NPU VLM hype.
  18. 329 viewsA $7 ESP32 Gives an AI Agent Hands on a Real iPhone While a 14M LLM Keeps a Fish AliveA cheap ESP32 becomes an AI agent's eyes and hands on a real iPhone, while a tiny distilled LLM runs an $8 virtual fish tank offline.
  19. 451 viewsThree ESP32 Builds Show How Far On-Device AI Has Come in a WeekAn open-vocabulary speech engine, a full offline voice assistant, and a new ESP32-P4 compute module show how much now runs on one microcontroller.
  20. 317 viewsA Pixel Phone Speeds Up On-Device Speech AI While a $2 Chip Learns to SeeArm's SME2 doubles streaming-ASR speed on a Pixel 11, a battery-sipping voice stack lands on Android, and two cheap microcontrollers go local.
  21. 394 viewsGoogle Open-Sources Its On-Device AI Engine While a Ternary LLM Shrinks a 30B Model to 12GBML Drift goes open source, ExecuTorch grows up on Cortex-M, a 1.58-bit MoE lands on a 12GB GPU, and two new boards hit the bench.
  22. 317 viewsA 384M LLM Learns to Call Tools From Scratch While Rockchip Chases 44 TOPS at the EdgeA from-scratch tiny LLM, a sub-1-bit quantization trick, a MoE model on a phone NPU, and two new chips round out today's edge sweep.
  23. 181 viewsA 4GB NVIDIA Model Learns to Chat With Robots While Raspberry Pi Gets a Local-LLM NPUNVIDIA's Nemotron Bolt talks to a Jetson-powered robot, Embedl speeds Jetson deployment, and two new boards push NPUs onto cheaper SBCs.
  24. 188 viewsIntel's NPU Learns to Guess Ahead While AMD and Intel Merge Their CPU AI PlaybooksIntel ships speculative decoding for NPUs and a Google bridge to them, AMD and Intel merge CPU math libraries, and two new boards push edge compute further.
  25. 224 viewsA $1 Microcontroller Stretches Toward a 4B LLM While Google Opens Its NPU BlueprintA $1 chip pushes an LLM toward 4B parameters, Google opens its Coral NPU compiler, and an ESP32 learns to hear offline in seven languages.
  26. 660 viewsFive ESP32 Builds Push Local AI From a Dev Board to a Drone's CameraA 28.9M LLM, two phone/voice agents, a new AI-ready dev board and a drone video hack all land on the same $7 chip family.
  27. 224 viewsA 30B AI Agent Learns to Live on One GPU While a 254M Model Learns to Listen OfflineMeta's 30B on-device agent, a 254M offline speech model, and a $10 ESP32 that hears without the cloud lead today's edge sweep.
  28. 302 viewsEdge Runtimes Learn to Run LLMs at 2 Bits While a New Chip Takes Aim at DGX SparkOllama, llama.cpp and PyTorch all shipped fresh runtime builds this week, and a 16-core SoC says it can match desktop AI boxes for less.
  29. 284 viewsA 27B AI Hits an iPhone's Neural Engine at 3 Bits While a 14M LLM Keeps a Fish Tank Alive on ESP32Apple's Neural Engine runs a 27B model at low bit-width, a distilled 14M LLM animates a $8 microcontroller pet, and new research questions KV-cache quant on Raspberry Pi.
  30. 253 viewsAn AI Racing Drone Beats Humans While a Jetson VLA Model Sprints 12x FasterA single-camera drone outflies champion pilots, a Jetson runtime slashes VLA latency, and Reachy Mini learns to remember people on a Pi.
  31. 300 viewsAMD Opens Its NPU Stack to AI Agents While Qualcomm Puts an LLM on Your FaceAMD ships an official NPU SDK, hobbyists wake up an older Ryzen chip's idle silicon, and new hardware arrives already quoting on-device LLM speeds.
  32. 532 viewsEdge AI Learns to Hear Without Any Dedicated AI Silicon At AllA microcontroller runs open-vocabulary speech recognition with no neural accelerator, while NPU boards and an $8 chip push tiny-LLM throughput further.
  33. 542 viewsESP32 Special: Two Offline Voice-AI Builds Debut While a New Chip Powers a Display BoardTwo fresh ESP32 voice-AI repos go fully offline, a mystery ESP32-S31 chip shows up on a display board, and an ESP32 radio hack learns to transmit.
  34. 224 viewsA 35B MoE Vision AI Learns to Fit a Phone While a $7 ESP32 Hijacks an iPhoneOpenBMB squeezes a 35B MoE vision model onto an iPhone, Google shrinks multimodal search to 191MB, and a $7 ESP32 learns to tap a real iPhone's screen.
  35. 405 viewsA Hexagon NPU Learns New AI Tricks While Edge Robots Get Lighter World Modelsllama.cpp opens a path to Qualcomm's Hexagon NPU, a 2-bit automation model surges on GitHub, and a lighter world model targets robot arms.
  36. 277 viewsA 1-Bit AI Trick Shrinks a 70B Model to Fit on a $200 GPUSamsung's sub-1-bit quantization paper gets a reality check, plus fresh research on tiny LLMs and ESP32 voice silicon.
  37. 283 viewsSmall AI Models Steer Robots While ESP32 Boards Do the Grunt WorkA dual-core Arduino runs robot policies on-device, a paper argues for skill-sized models over one big brain, and two ESP32 boards ship.
  38. 343 viewsWindows Learns GGUF as AI Agents Design Their Own Inference ChipMicrosoft wires llama.cpp into Windows ML's NPU stack while an agent-built FPGA accelerator and fresh AI PC benchmarks show where edge inference actually stands.
  39. 266 viewsA 14M-Parameter LLM Keeps a Virtual Fish Tank Alive on an $8 ChipA distilled LLM runs a fish tank on an $8 ESP32-S3, four Raspberry Pi 5s share a 30B model, and a 2B decision model lands for edge agents.
  40. 485 viewsESP32 Special: Cloud Voices and an E-Ink Reader, No New On-Device LLM YetTwo ESP32 voice projects lean on cloud AI while a maker's e-ink reader builds the hardware the next on-device model will need.
  41. 292 viewsMeta Opens Muse to ESP32 Makers as a Tiny LLM Learns to Remember a Hidden ObjectMeta ships ESP32 and Linux SDKs for its Muse AI, Qualcomm's next phones get 2nm NPUs, and a 68KB brain gives a cheap robot arm memory.
  42. 409 viewsExecuTorch Hits 1.0 as llama.cpp Learns to Make Instant AI DecisionsPyTorch declares its on-device AI runtime production-ready while llama.cpp adds a decision-model endpoint and two new NPU modules land for edge boards.
  43. 462 viewsSeven $5 Chips Learn to Share an LLM, One Bit at a TimeA BitNet cluster splits an LLM across seven ESP32-S3 boards, a 2-bit tool-calling model lands on GitHub, and a quantization paper gets llama.cpp 15x faster on an M4 Pro.
  44. 513 viewsA 4B AI Model Learns to Run a Robot Arm Entirely on Jetson ThorNVIDIA's Cosmos 3 Edge drives a robot arm on-device, a $5-class chip gets a voice it hasn't spoken yet, and two new boards widen the SBC lineup.
  45. 325 viewsAn NPU-Only Runtime Lands for Ryzen AI as a Vintage Terminal Learns to Think OfflineA 17MB runtime puts LLMs entirely on AMD's XDNA2 NPU, an old terminal gets an offline brain, and Intel's NPU gets unlocked by reverse engineering.
  46. 485 viewsA 312K-Parameter LLM Learns to Flip Switches as Pi Prices Climb AgainA tiny GPIO-control model and a Japanese TTS join the ESP32 pile-up while Raspberry Pi raises prices and a Jetson robot chases bubbles.
  47. 318 viewsESP32 Special: Small LLMs Learn to Chat, Listen and Keep the Fish AliveA full day inside the ESP32 world: chatty microcontroller LLMs, a $5-chip speech model, and two new boards from Espressif's own community.
  48. 422 viewsWearable AI Chips Land as an ESP32 Board Learns to Run a Full Offline Voice LoopFrom a Qualcomm earbud chip to an ESP32-S3 that hears, thinks and speaks with no cloud, edge AI keeps shrinking into pockets and ears.
  49. 495 viewsA $300 GPU Streams a 177B AI Model From an SSD While llama.cpp Learns to Skip AheadCommunity builders push token throughput further this week — via SSD-streamed MoE experts, prompt-lookup drafting, and a wrapper for Apple's built-in on-device LLM.
  50. 198 viewsA Classifier That Only Picks, a Model That Skips Tokens, and an AI Firm Bets 2.6B Parameters Can Do Agent WorkLiquid AI ships a 2.6B agentic model for edge hardware, a 144M classifier skips text generation entirely, and a new paper shows byte-level LLMs can beat tokenized ones with sc
  51. 343 viewsNeedle Threads a Raspberry Pi, an NPU Learns to Move a Robot Arm Fast, and a Biped Joins the LLM ToolkitA tool-calling model flips switches on a Pi 5, a Qualcomm NPU speeds up a robot arm sevenfold, and a $2,500 biped joins LeRobot.
  52. 305 viewsNPUs Learn to Fuse: AMD Opens Its XDNA Compiler, Qualcomm Previews Linux, and Two New On-Device AI Models LandAMD open-sources fused FlashAttention kernels for XDNA NPUs, Qualcomm ships a Linux preview for Snapdragon X2, and fresh research pushes tiny and trillion-scale models toward
  53. 639 viewsA Diffusion Model and a 28.9M LLM Both Now Run on Bare MicrocontrollersAn RP2350 draws faces from noise, an ESP32-S3 writes stories, and AI smart glasses squeeze in a 1-bit model — all without a server.
  54. 291 viewsThe ESP32 Beat Skips the LLM Today: A Desk Companion, Drumsticks, and a JavaScript OSThree ESP32 builds this week show the chip's range — a reactive desk companion, motion-sensing drumsticks, and a scripting OS — none of them running a language model.
  55. 254 viewsTiny Audio AI Models Learn to Whisper Without Ever Calling HomeTwo new speech stacks and a tool-calling model push voice AI fully on-device, while Nordic and Zephyr quietly harden the hardware underneath.
  56. 305 viewsllama.cpp's Nightly Grind Teaches Phone Chips New AI Tricks While NVIDIA Ships a Rival Edge RuntimeSmall llama.cpp builds keep adding Hexagon DSP ops, NVIDIA's TensorRT-Edge-LLM adds Day-0 model support, and a new leaderboard measures tokens per joule.
  57. 306 viewsA 27B AI Model Shrinks to 5.9GB as Ternary Quantization Keeps Pushing the Floor DownPrismML compresses a 27B model to 5.9GB, Intel's BITCOS beats the 1.585-bit ternary limit, and a 44M-parameter model claims exact arithmetic on a laptop CPU.
  58. 317 viewsA 4B AI Model Drives a Robot Arm on Jetson Thor, No Datacenter in the LoopNVIDIA post-trains Cosmos 3 Edge for on-device manipulation, a PKU lab ships a llama.cpp engine for VLA policies, and Jetson's next Orin Nano gets a ship date.
  59. 356 viewsAI PCs Go Big: A 300B-Parameter Desktop, an 80-TOPS Mini PC, and Edge NPUs Redraw the Local-Inference MapGMKtec, ASUS and Radxa all shipped NPU hardware this week while OpenVINO and a Qualcomm robotics runtime pushed what those chips can actually run.
  60. 463 viewsJetson Thor Sprints Past llama.cpp While a 15M-Parameter LLM Still Fits an $8 ChipNVIDIA posts a 6.4x MLPerf edge win on Jetson AGX Thor, a dense TinyStories model skips the flash trick, and a paper splits VLA robots between cloud and a tiny local model.
  61. 284 viewsESP32 Special: An $8 Chip Runs a 29-Million-Parameter LLM, and Vendors Rethink the Board Around ItA one-chip LLM, a Wi-Fi upgrade to Seeed's tiny displays, and Tuya's push to make ESP32 an AI-agent target, not just a Wi-Fi one.
  62. 251 viewsA Wristband Reads Muscles, a Ring Wants Your Ideas: Edge AI Moves Onto the BodyNew wearable and phone releases push transcription, gesture control and silent speech fully on-device, while ESP32 and Jetson tooling keeps pace.
  63. 336 viewsRuntimes on the Move: llama.cpp, ExecuTorch and LiteRT All Update as Edge AI's Software Layer Speeds Upllama.cpp shipped two builds in two days, ExecuTorch hit 1.0 with new NPU backends, and LiteRT tuned fp16 kernels for mobile CPUs.
  64. 269 viewsTernary Weights and Tiny Tanks: Small-Model Quantization Gets Concrete for Edge AIA ternary 8B model, a BitNet toy for TinyStories, a fish tank run by a 14M LLM, and a Rust retrieval encoder push quantization research toward real hardware.
  65. 283 viewsSplit-Brain Robots: Jetson Handles the Vision, a $49 MCU Kit Handles the Milliseconds — Edge AI Keeps Dividing the JobA student-built quadruped, a walking-robot policy on a Rockchip SBC, a tiny STM32N6 vision camera, and a $49 TinyML kit all landed this week.
  66. 354 viewsQualcomm Chases 30B AI Models on a Phone as Edge Silicon Keeps MultiplyingA phone NPU claims 30B MoE inference, a 35B model streams from storage on a Mac, and an XDNA1 NPU gets a Linux bring-up.
  67. 188 viewsA $1 Microcontroller Learns to Dream Faces as On-Device AI Keeps ShrinkingAn RP2350 chip runs a diffusion model, an ESP32-S3 speaks Japanese, and researchers tackle mobile power and tiny-drone control at the edge.
  68. 189 viewsA 90-Million-Parameter LLM Talks From a 2004 PSP, While On-Device AI Keeps Finding Smaller HomesA modded Sony PSP runs a tiny LLM, a $3 chip learns to speak, and a 2B open model claims agentic skills for phones.
  69. 209 viewsOne Toolkit, One Chip, One Watch: On-Device AI Keeps Colonizing the Phone LayerA GitHub toolkit, a 100MB cloning TTS, a Pi-powered dashcam agent, and a phone-to-watch AI rollout — all inference staying on the device.
  70. 251 viewsRuntimes Race Ahead: llama.cpp 0.4.0 and a 30B On-Device AI Agent Test the Edge's LimitsA new llama.cpp release, an ExecuTorch-powered 30B agent model, a cheap RK3576 vision board, and a DIY Jetson robot dog mark a busy week for edge toolchains.
  71. 237 viewsQuantization Papers Pile Up as Researchers Argue Over Where Small AI Should Spend Its BitsFresh arXiv work rethinks quantization strategy and sustainability, an Apple-adjacent paper shrinks the dictation encoder, and new silicon and Jetson guidance round out the ed
  72. 226 viewsRobot Policies Start Running Like Local AI Chatbots — Straight on the DeviceA llama.cpp-style engine ports VLA robot policies to Jetson, NVIDIA doubles entry-level robotics compute, and a $10 chip proves the floor of local AI.
  73. 335 viewsAMD, Qualcomm and NVIDIA All Chase the Same Local-AI Bottleneck: MemoryThree chipmakers and a mini-PC builder all attack the same problem this week: getting AI inference closer to memory, not just closer to silicon.
  74. 173 viewsA Microcontroller Learns to Retrain Itself as On-Device AI Keeps Multiplying TasksFresh arXiv work tackles MCU vision drift and phone LLM memory pressure, while a solar bird feeder and a desktop WALL-E show the hobbyist edge staying busy.
  75. 228 viewsA Solo Coder Brings Vision to a Local LLM as Edge Silicon and TinyML Builders Push Back the FrontierDeepSeek V4 Flash gains on-device vision on a Mac, a $1 chip draws pictures, and Qualcomm ships new edge silicon ahead of IFA.
  76. 453 viewsA Million-Token LLM Tries to Fit On Your Phone as Tiny Voice Models MultiplyAn iFLYTEK spin-off open-sources a 1.7B model claiming native million-token context on-device, while a 14MB tool-caller and an open voice-agent LLM push the small-model race f
  77. 280 viewsllama.cpp Teaches an NPU to Share the Load as Small AI Engines Keep Multiplyingllama.cpp adds multi-NPU Hexagon support, ONNX Runtime brings quantized KV caches to the browser, and a solo Rust engine beats llama.cpp on tiny models.
  78. 192 viewsA 27B LLM Shrinks to Phone Size as Edge Quantization Keeps Rewriting the RulesA 1-bit Qwen derivative fits an iPhone, a healing trick beats its own teacher at 4-bit, and a dense LLM limps along on an $8 chip.
  79. 205 viewsA Duck Robot Runs Its Balance Loop On-Chip as Local AI Quantization Claims Get AuditedA Rockchip-powered duck robot, two offline Raspberry Pi builds, and audits exposing quantization's blind spots and mislabeled GGUF files.
  80. 201 viewsIntel's Wildcat Lake Brings a Modest NPU to AI PCs, While Edge AI Claims It's Going Mainstream in IoTIntel details a 17 TOPS NPU chip built for chiplets, and an industry trend piece argues edge inference is leaving the pilot stage — both light on independent proof so far.
  81. 237 viewsIBM Ships an Edge-First Granite LLM as RISC-V AI Boards Keep Fragmenting the ToolchainIBM's Granite 4.2 targets edge devices with a 3B open model, while a new RISC-V AI pocket computer ships locked to its own OS fork.
  82. 284 viewsJetson Orin Nano 2 Doubles Edge Robotics AI, While Local LLM Agents Get a Bigger Home on the DesktopNVIDIA doubles its entry robotics brain, Perplexity moves agents onto local GPUs, and Liquid AI ships a speedup and a benchmark suite for on-device models.
  83. 262 viewsHearing Aids Get Their Own AI Chips as On-Device Voice and Vision Push Past the PhoneHearing aids ship dedicated on-device AI chips, new AI glasses land, and real-phone benchmarks show why raw specs don't tell the whole story.
  84. 463 viewsMeta's Muse Glimmer Bets Big on On-Device Agentic AI as the Runtime Wars Keep MultiplyingMeta ships an on-device agentic model, an MoE engine claims 753B on one GPU, and researchers find 10 CVEs in a local inference engine.
  85. 254 viewsLiquid AI Trains Its Way Around the Q4_0 Quality Tax, While New Papers Chip Away at What Quantization Quietly BreaksLiquid AI distills instead of just rounding for 4-bit LFM2.5 checkpoints, as fresh research flags what low-bit quantization costs in memory and multilingual accuracy.
  86. 349 viewsEdge Dispatch: NVIDIA Squeezes a 4B World Model Onto the Robot Itself as Liquid AI and AMD Chase the Same EdgeA Jetson Thor robot policy, a GGUF port for VLA models, a 2.6B tool-calling LLM, and a new AMD robotics module — all inference, no data center.
  87. 356 viewsAMD's Ryzen AI Halo Jumps to 192GB While Qualcomm Pushes On-Device AI AgentsAMD bumps its NPU mini PC to 192GB of unified memory, Qualcomm ships five agentic apps for Snapdragon X, and Korea rethinks its NPU strategy.
  88. 288 viewsA Robot Arm Joins the NPU Party: FastFlowLM Adds a Vision-Language-Action Model to Ryzen AIFastFlowLM's first stable release puts a robotics policy on Ryzen AI's NPU, while Korea ships a boxed NPU appliance and a Raspberry Pi learns to narrate what it sees.
  89. 280 viewsKorea's KT Ships a Boxed NPU LLM Station While the ESP32 Crowd Trims Memory FurtherA Korean telecom sells an all-in-one on-prem LLM box built on a domestic NPU, while ESP32 tinkerers keep shrinking what a model needs to run.
  90. 251 viewsRyzen AI's NPU Runtime Goes Official While a Raspberry Pi Learns to See and Speak with a Tiny LLMAMD folds a hobbyist NPU runtime into ROCm, Google shows Gemma driving a robot from a Raspberry Pi 5, and a 45M-parameter model books tool calls on a phone.
  91. 249 viewsRaspberry Pi's GPU Joins the AI Party While a 14MB Model Learns to Call ToolsA Raspberry Pi 5 runs Gemma and vision models split across CPU and GPU, and a 45M-parameter model fits tool-calling into 28MB of RAM.
  92. 265 viewsThe $8 AI Chip Grows a Coffee Habit: ESP32 Tiny-LLM Trick Gets a Second ModelA new 'Barista' model and a closer look at Google's Per-Layer Embeddings trick show what running an LLM on a microcontroller can and can't do.