Chris Novick
Computer engineer. Writing on systems, local models, Rust, and engineering.
Writing
Finance Isn't Boring. You Just Never Saw the Machine.
Most engineers got exactly one formal brush with this world: an economics course somewhere in undergrad. Macro, probably. Maybe micro. Supply and demand curves,...
How I got Qwen3.8 27B decoding 2.4x faster on an AMD R9700
After the 3090 work, a friend gave me remote access to an AMD Radeon AI PRO R9700 (RDNA4, gfx1201). I'd never done inference on AMD before. I wanted to know how...
How I made Qwen3.8 27B decode 1.8x faster at 109K context on one RTX 3090 Ti
I run Qwen3.8 27B (4-bit, W4A16) on two 24 GB Ampere cards, an RTX 3090 Ti and an RTX 3090, each with at least 128K of context. Over three days (Sep 24 to 26, 2026)...
How I forked vLLM and made Qwen3.8-Flash-Next decode 1.6x faster on one GPU
I run Qwen3.8-Flash-Next on one RTX PRO 6000 Blackwell as my daily local model. Over two days (Sep 23 to 24, 2026) I tuned the serving stack. Decode went from about...
The Computer Still Exists, Anon
I just came across this site that claims you're under water financially for 40+ years if you buy inference hardware to run local models. It completely ignores the...
Imposter Syndrome and Power law distributions
Many new engineers will hit a moment in their professional career, often early on, where they feel miles behind their peers in domain knowledge and ability. A terse...