Research desk

Reproducible findings, not hot takes

Technical reporting for reverse engineering, cloud security labs, vulnerability analysis, and defensive testing.

Data graphic: Best local LLM: 16GB. gpt-oss-20b 12.8GB; Gemma 4 26B A4B 14.2GB; Devstral Small 2 14.3GB; Qwen3.5-9B 5.68GB; Gemma 4 12B 6.98GB

Best Local LLM for 16GB in 2026: RTX 5060 Ti, 4060 Ti and Mac mini M4 (Coding First)

gpt-oss-20b and Gemma 4 26B A4B lead on 16GB NVIDIA cards, while a 16GB Mac mini M4 is better served by Qwen3.5-9B. File sizes, context limits and VRAM math.

Data graphic: Which box for local LLMs?. DGX Spark $4,699; Mac Studio M5 Ultra from $5,499; Ryzen AI Max+ 395 from $3,449

Nvidia Dgx Spark Research

DGX Spark vs Mac Studio M5 Ultra vs Ryzen AI Max+ 395: Which Box for Local LLMs?

Price per GB, memory bandwidth, prefill vs decode on gpt-oss-120b, clustering and software stacks: which unified-memory desktop fits your local LLM work.

Data graphic: Copilot Pro vs Pro+. Pro $10 → 1,500 credits; Pro+ $39 → 7,000 credits; Max $100 → 20,000 credits; 1 credit $0.01; Completions Unlimited

Github Copilot Research

GitHub Copilot Pro vs Pro+ After AI Credits: What $10 vs $39 Actually Buys

Copilot now bills in AI credits at $0.01 each. Here is what Pro's 1,500 and Pro+'s 7,000 credits buy per model, and when Pro+ beats Claude or Cursor.

Data graphic: Coding agent CLIs compared. Claude Code from $20 / mo; Codex CLI Apache-2.0; Antigravity CLI agy; OpenCode MIT

Claude Code Research

Claude Code vs Codex CLI vs Antigravity CLI vs OpenCode: Coding Agents Compared (2026)

Gemini CLI is gone for consumer plans. We compare Claude Code, Codex CLI, Google's agy and OpenCode on price, models, license, sandboxing and MCP.