https://www.youngju.dev/blog 천천히 올바르게. AI Researcher & DevOps Engineer Youngju's tech blog. GPU/CUDA, LLM, MLOps, Kubernetes AI workloads, distributed training, and data engineering. ko fjvbn2003@gmail.com (Youngju Kim) fjvbn2003@gmail.com (Youngju Kim) Sat, 16 May 2026 00:00:00 GMT https://www.youngju.dev/blog/culture/2026-05-16-edge-ai-tinyml-2026-litert-executorch-edge-impulse-jetson-coral-hailo-sipeed-k230-llama-cpp-deep-dive.en https://www.youngju.dev/blog/culture/2026-05-16-edge-ai-tinyml-2026-litert-executorch-edge-impulse-jetson-coral-hailo-sipeed-k230-llama-cpp-deep-dive.en A full-stack map of the 2026 Edge AI / TinyML ecosystem — the dual standard formed after TFLite Micro was rebranded as LiteRT and ExecuTorch reached GA, the TinyML cloud workflow created by Edge Impulse, the accelerator showdown between NVIDIA Jetson Orin Nano/NX/Thor/AGX and Coral Dev Board, the rise of Israeli Hailo-15/8 and Chinese Sipeed K230 (RISC-V + NPU), the SBC standardization of Rockchip RK3588, MaixPy / Arduino Nano 33 BLE Sense / Seeed Wio AI, MicroPython for ML, and on-phone MLC LLM / llama.cpp / Whisper.cpp / GGUF — covering Phi-3/3.5/4, Gemma 2/3, Llama 3.2 1B/3B — and how IoT / mobile / automotive engineers should pick tools in the age of Always-on AI, including case studies from Korea (ETRI / Samsung / LG) and Japan (Sony AI / NTT). Sat, 16 May 2026 00:00:00 GMT fjvbn2003@gmail.com (Youngju Kim) edge-aitinymltflite-microlitertexecutorchedge-impulsejetson-orincoral-dev-boardhailosipeed-k230rockchip-rk3588maixpymicropython-mlonnx-runtime-mobilecore-mltensorrtapache-tvmmlc-llmwhisper-cppllama-cppggufphi-3phi-4gemmallama-3-22026deep-diveenglish https://www.youngju.dev/blog/culture/2026-05-16-edge-ai-tinyml-2026-litert-executorch-edge-impulse-jetson-coral-hailo-sipeed-k230-llama-cpp-deep-dive.ja https://www.youngju.dev/blog/culture/2026-05-16-edge-ai-tinyml-2026-litert-executorch-edge-impulse-jetson-coral-hailo-sipeed-k230-llama-cpp-deep-dive.ja 2026 年のエッジ AI / TinyML エコシステムをフルスタックで俯瞰 — TFLite Micro が LiteRT へリブランドされ ExecuTorch が GA となって形成された二大標準、Edge Impulse が築いた TinyML クラウドワークフロー、NVIDIA Jetson Orin Nano/NX/Thor/AGX と Coral Dev Board のアクセラレータ対決、イスラエルの Hailo-15/8 と中国の Sipeed K230(RISC-V+NPU)の台頭、Rockchip RK3588 の SBC 標準化、MaixPy / Arduino Nano 33 BLE Sense / Seeed Wio AI、ML 向け MicroPython、そしてスマホ上で動く MLC LLM / llama.cpp / Whisper.cpp / GGUF — Phi-3/3.5/4、Gemma 2/3、Llama 3.2 1B/3B まで — Always-on AI の時代に IoT / モバイル / 自動車エンジニアがどう道具を選ぶべきかを、韓国(ETRI / Samsung / LG)と日本(Sony AI / NTT)の事例とともにまとめます。 Sat, 16 May 2026 00:00:00 GMT fjvbn2003@gmail.com (Youngju Kim) edge-aitinymltflite-microlitertexecutorchedge-impulsejetson-orincoral-dev-boardhailosipeed-k230rockchip-rk3588maixpymicropython-mlonnx-runtime-mobilecore-mltensorrtapache-tvmmlc-llmwhisper-cppllama-cppggufphi-3phi-4gemmallama-3-22026deep-dive日本語 https://www.youngju.dev/blog/culture/2026-05-16-edge-ai-tinyml-2026-litert-executorch-edge-impulse-jetson-coral-hailo-sipeed-k230-llama-cpp-deep-dive https://www.youngju.dev/blog/culture/2026-05-16-edge-ai-tinyml-2026-litert-executorch-edge-impulse-jetson-coral-hailo-sipeed-k230-llama-cpp-deep-dive 2026년 엣지 AI / TinyML 생태계의 풀스택 지도 — TFLite Micro 가 LiteRT 로 리브랜드된 후 ExecuTorch 가 GA 가 되며 형성된 듀얼 표준, Edge Impulse 가 만든 TinyML 클라우드 워크플로, NVIDIA Jetson Orin Nano/NX/Thor/AGX 와 Coral Dev Board 의 가속기 격돌, 이스라엘 Hailo-15/8 과 중국 Sipeed K230(RISC-V+NPU) 의 부상, Rockchip RK3588 의 SBC 표준화, MaixPy/Arduino Nano 33 BLE Sense/Seeed Wio AI, MicroPython for ML, 그리고 폰 위에서 도는 MLC LLM / llama.cpp / Whisper.cpp / GGUF — Phi-3/3.5/4, Gemma 2/3, Llama 3.2 1B/3B 까지 — Always-on AI 의 시대에 IoT / 모바일 / 자동차 엔지니어가 어떤 도구를 어떻게 골라야 하는지 한국(ETRI/삼성/LG)과 일본(Sony AI/NTT) 사례까지 모두 정리합니다. Sat, 16 May 2026 00:00:00 GMT fjvbn2003@gmail.com (Youngju Kim) edge-aitinymltflite-microlitertexecutorchedge-impulsejetson-orincoral-dev-boardhailosipeed-k230rockchip-rk3588maixpymicropython-mlonnx-runtime-mobilecore-mltensorrtapache-tvmmlc-llmwhisper-cppllama-cppggufphi-3phi-4gemmallama-3-22026deep-dive https://www.youngju.dev/blog/culture/2026-05-16-open-source-llms-2026-llama-4-deepseek-v3-r1-qwen-3-mistral-large-2-phi-4-gemma-3-falcon-3-deep-dive.en https://www.youngju.dev/blog/culture/2026-05-16-open-source-llms-2026-llama-4-deepseek-v3-r1-qwen-3-mistral-large-2-phi-4-gemma-3-falcon-3-deep-dive.en In spring 2026, open-source LLMs are no longer the shadow of closed models. Meta Llama 4 (Scout 109B, Maverick 400B MoE, Behemoth 2T), Llama 3.3 70B as the last dense baseline, DeepSeek V3 671B MoE and the R1 reasoning model, Alibaba Qwen 3 and Qwen 2.5 Coder, Mistral Large 2 123B with Pixtral / Codestral / Ministral, Microsoft Phi-4 14B with synthetic data, Google Gemma 3 multimodal, TII Falcon 3 and Falcon Mamba hybrid, Allen AI OLMo 2 and Tülu 3 fully open, plus HyperCLOVA X / Kanana / EXAONE 3.5 in Korea, ELYZA / PLaMo / Sakana in Japan, Yi / InternLM / MiniCPM in China — the full vLLM / SGLang / llama.cpp inference stack and license map in one read. Sat, 16 May 2026 00:00:00 GMT fjvbn2003@gmail.com (Youngju Kim) open-source-llmllama-4deepseekqwenmistralphi-4gemma-3falconolmokananaenglish https://www.youngju.dev/blog/culture/2026-05-16-open-source-llms-2026-llama-4-deepseek-v3-r1-qwen-3-mistral-large-2-phi-4-gemma-3-falcon-3-deep-dive.ja https://www.youngju.dev/blog/culture/2026-05-16-open-source-llms-2026-llama-4-deepseek-v3-r1-qwen-3-mistral-large-2-phi-4-gemma-3-falcon-3-deep-dive.ja 2026年春、オープンソースLLMはもはやクローズドモデルの影ではない。Meta Llama 4 (Scout 109B、Maverick 400B MoE、Behemoth 2T)、Llama 3.3 70Bの最後のデンスベースライン、DeepSeek V3 671B MoEとR1推論モデル、Alibaba Qwen 3とQwen 2.5 Coder、Mistral Large 2 123BとPixtral・Codestral・Ministral、Microsoft Phi-4 14Bの合成データ学習、Google Gemma 3マルチモーダル、TII Falcon 3とFalcon Mambaハイブリッド、Allen AI OLMo 2とTülu 3の完全公開、韓国のHyperCLOVA X・Kanana・EXAONE 3.5、日本のELYZA・PLaMo・Sakana、中国のYi・InternLM・MiniCPMまで — vLLM・SGLang・llama.cpp推論スタックとライセンスマップを一気に整理する。 Sat, 16 May 2026 00:00:00 GMT fjvbn2003@gmail.com (Youngju Kim) open-source-llmllama-4deepseekqwenmistralphi-4gemma-3falconolmokanana日本語 https://www.youngju.dev/blog/culture/2026-05-16-open-source-llms-2026-llama-4-deepseek-v3-r1-qwen-3-mistral-large-2-phi-4-gemma-3-falcon-3-deep-dive https://www.youngju.dev/blog/culture/2026-05-16-open-source-llms-2026-llama-4-deepseek-v3-r1-qwen-3-mistral-large-2-phi-4-gemma-3-falcon-3-deep-dive 2026년 봄, 오픈소스 LLM은 더 이상 폐쇄형의 그림자가 아니다. Meta Llama 4(Scout 109B, Maverick 400B MoE, Behemoth 2T), Llama 3.3 70B 마지막 덴스 베이스라인, DeepSeek V3 671B MoE와 R1 추론 모델, Alibaba Qwen 3와 Qwen 2.5 Coder, Mistral Large 2 123B와 Pixtral·Codestral·Ministral 라인, Microsoft Phi-4 14B 합성 데이터 학습, Google Gemma 3 멀티모달, TII Falcon 3와 Falcon Mamba 하이브리드, Allen AI OLMo 2와 Tülu 3 완전 공개, 한국의 HyperCLOVA X·Kanana·EXAONE 3.5, 일본의 ELYZA·PLaMo·Sakana, 중국의 Yi·InternLM·MiniCPM까지 — vLLM·SGLang·llama.cpp 추론 스택과 라이선스 지도를 한 호흡으로 정리한다. Sat, 16 May 2026 00:00:00 GMT fjvbn2003@gmail.com (Youngju Kim) open-source-llmllama-4deepseekqwenmistralphi-4gemma-3falconolmokanana