Articles for people who
ship the stack
Rewrites on React, Node.js, TypeScript and AI. A translated body is shown when it exists. If it does not, you see the English text and a note that says so.
Tagged: Benchmarks
TensorFold vs llama.cpp on a Mac Studio M5 Ultra: 1.84x the Throughput on Real JSON Work
I benchmarked TensorFold 1.2.0 against llama.cpp on a Mac Studio M5 Ultra with Qwen3.8-27B and 80 real JSON requests: 1.84x throughput at 8 concurrent.
9 min readHy-MT2-7B on Five Local Runtimes: Which One Should Serve Translation on a Mac?
Hy-MT2-7B load-tested on llama.cpp, LM Studio, mlx-lm, Ollama and MLX-Serve on two Mac Studio M5 Ultra machines: throughput, scaling, determinism, memory.
9 min readGemini 3.8 Flash at Launch: Speed, Pricing Deadline and Safety Caveats
A review of Gemini 3.8 Flash: official benchmark gains, a 304 tokens-per-second snapshot, promo pricing ending in 2027, the Cyber model and a multilingual safety dip.
7 min readWhy Dual RTX 3090s Hit 55 tok/s Instead of 220 with SGLang and DFlash2
A hands-on look at running Qwen3.8-27B on two 3090s with SGLang, and how PCIe x4 links, missing P2P, tight KV cache and power spikes crushed the advertised speed.
7 min readMiniCPM5-2B vs 4B Rivals: Why an Agentic Harness Tells a Different Story
MiniCPM5-2B beats 4B rivals on single-shot scores, then falls two to three times behind in agentic harnesses. The benchmark mix-up and Ollama throughput.
10 min readAgents Pay Dearly for Waiting: Polling, Blocking and Tasks Compared
A benchmark of three ways an agent can wait on a slow cloud operation: polling, blocking and MCP tasks, the token cost of each, and rules for tool designers.
8 min readAgent Harness From Scratch: Six Stages and an Experiment That Isolates Gains
A harness can move benchmark scores more than the model. Build a small agent harness in six stages and test one change at a time to see what actually helped.
7 min readGraphRAG or Plain RAG? Where Graphs Help, Where They Cost Too Much
GraphRAG vs RAG: graphs win on multi-step reasoning and global summaries but lose on simple lookups and cost more. Benchmark numbers and when to pick each.
7 min readWhy Agent Memory Benchmarks Mislead, and How to Evaluate on Your Own Data
Agent memory benchmarks mislead with flawed answer keys and graders. Test retrieval apart from answers, add recency, abstention and forgetting checks.
15 min read
About these articles
Request a 24h estimate
Need the same stack in a production operator layer? Send the brief — estimate within 24 hours.