11 posts on SDAD Writes.
Kaggle's free 2x T4 accelerator became hard to get this month. I traced why: 53 YouTube tutorials with 612,813 views teaching people to run LLMs on Kaggle around the clock, 80% of that reach landing in a single 16-day format-cloning wave. Here is the full anatomy of how a shared resource gets eaten.
A complete voice AI stack, speech to text, a 2B language model, and text to speech, running fully local on a 2013-era CPU server with no GPU. I benchmarked every stage, audited the marketing claims, and the "150 tokens per second" pitch came out 13.6x slower in reality. Here is what a local voice assistant actually costs and does.
I audited every claim on the Spark-X2.5 model cards and stress-tested both the 4B and 1.7B on agentic coding tasks over two Tesla T4s. The 4B is a genuinely usable small coding agent. The 1.7B is an assistant, not an agent. And both models have a thinking-verbosity tax worth knowing about.
I ran the first head-to-head of the two open "System One" decision models, Laya and Jev, on 751 byte-identical inputs: same states, same questions, same seed, question hashes verified before comparing. Jev wins most suites for $0.008. Laya wins where it counts for a free model. A fourth column with Qwen 1.5B under constrained decoding completed the picture.
I stress-tested Ternary Bonsai 2 27B on two Tesla T4s: 15 tokens per second on a single weak GPU, the full 262k context loading in 26GB of VRAM, and a complete todo webapp built and self-tested inside a local coding agent. The claims mostly check out, with a few catches.
I benchmarked LFM2.5 350M and Qwen3.5-2B on my iPhone SE 2 (2020) with 3GB of RAM using the PocketPal app. One model hits 70 tokens per second. The other needs 22 minutes for a single pass. Here is where the line is.
Two developments are breaking NVIDIA's CUDA monopoly: the Vulkan compute backend for llama.cpp (cross-vendor LLM inference on any GPU) and the Mojo programming language (a CUDA alternative that compiles to any accelerator).
AMD's $1500 Strix Halo runs the same 120B model as Nvidia's $4700 DGX Spark, only 13% slower. But DGX Spark wins prefill by 3x and compute by 13x. Full benchmarks, India pricing, and a hands-on check on 2x DGX Spark GB10 with a 30B Q4 model.
Every AI system runs on one of five chip types — CPU, GPU, TPU, LPU, or NPU. Each makes a different tradeoff between flexibility and speed. This guide explains all five in plain English, with enough depth to actually help you decide which one matters for your work.
No cluster, no budget, no PhD — just a MacBook Air with 8GB of RAM, a gaming PC, and every free GPU I could find. How I abliterated 38 models (97k+ downloads), rebranded the entire collection, and ended up decensoring models I trained myself.
Why I built my own blogging platform, what I actually work on — LLM gateways, security agents, self-hosted everything — and what you'll find written here.
