Tag: #phi-4
Writing on GPUs, LLMs, MLOps, Kubernetes — and mindset · 2 posts
Open-Source LLMs 2026 Deep Dive - Llama 4 · DeepSeek V3 + R1 · Qwen 3 · Mistral Large 2 · Phi-4 · Gemma 3 · Falcon 3
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 m
2026-05-16 · 32 min read #open-source-llm#llama-4#deepseek#qwen#mistralEdge AI & TinyML 2026 — LiteRT / ExecuTorch / Edge Impulse / Jetson / Coral / Hailo / Sipeed K230 / llama.cpp / Phi-4 Deep-Dive Guide
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
2026-05-16 · 32 min read #edge-ai#tinyml#tflite-micro#litert#executorch