Thoughts on Clean Code, Automation, and Web Architecture.

Freelancing ⏱ 6 min read

I’ve Lost 60% of My Leads in 7 Months — Here’s What I’m Doing Wrong

Nassim SADI July 27, 2026

AI & Local LLMs ⏱ 8 min read

Quantization for 8GB VRAM: Q4_K_M vs IQ4_XS vs UD-IQ4_NL

Nassim SADI July 19, 2026

AI & Local LLMs ⏱ 7 min read

9 Models Tested, 3 Rejected: What I Learned From 32 Benchmarks

Nassim SADI July 19, 2026

AI & Local LLMs ⏱ 7 min read

My 3-Model Local AI Stack: Fast Worker + Coder + Senior Planner

Nassim SADI July 18, 2026

AI & Local LLMs ⏱ 8 min read

Gemma 4 vs Qwen vs Ornith: Which Local LLM Codes Best on 8GB

Nassim SADI July 18, 2026

AI & Local LLMs ⏱ 7 min read

turbo2 vs turbo3 vs turbo4: Which KV Cache Quantization Fits Your VRAM

Nassim SADI July 17, 2026

AI & Local LLMs ⏱ 6 min read

Speculative Decoding Explained: How MTP Turns 18 t/s Into 36 t/s

Nassim SADI July 17, 2026

AI & Local LLMs ⏱ 9 min read

Asymmetric KV Cache: Why Compressing V More Than K Unlocks 128k

Nassim SADI July 16, 2026

AI & Local LLMs ⏱ 8 min read

Ornith 35B on 8GB VRAM: 128k Context at 30 t/s

Nassim SADI July 16, 2026

Web Design ⏱ 9 min read

I Fit a 35B Model Into 8GB VRAM. Heres the Full Setup.

Nassim SADI July 15, 2026

Web Design ⏱ 10 min read

My Full Local AI Benchmark: 32 Runs, 9 Models, 8GB VRAM

Nassim SADI July 15, 2026

Development ⏱ 5 min read

How I Hand Off WordPress Sites (And the Client Who Ghosted Me)

Nassim SADI May 24, 2026