Patrick Gawron

Articles

9 long-form essays. Deep dives, opinions, tutorials.

Ref PG-ART-008 Date 2026-07-27 Category LLM Read 7 min

LLM licenses: open weights are not open source

Apache, MIT, Llama Community, Gemma terms and the new OpenMDW-1.1 - what each one obliges you to do, which model families use it, and the three traps that are not in the licence name.

Read article >
Ref PG-ART-007 Date 2026-07-21 Category Coding Agent Read 7 min

Prewalk: swap to a cheap model after the first edit

A coding agent spends most of its money reading, not writing. Prewalk lets an expensive model do the reading, then hands the whole context to a cheap model at the exact right moment: the first edit.

Read article >
Ref PG-ART-004 Date 2026-04-30 Category Llama Cpp Read 4 min

How well does an RTX 4090 run Qwen3.6-27B?

43 words a second. 0.29 second wait. 20 of 20 coding answers correct. 19.5 GB used out of 24. The card runs this AI very well - and it can hold a 128k window with 4 chats at the same time.

Read article >
Ref PG-ART-003 Date 2026-04-29 Category Llama Cpp Read 4 min

How well does an RTX 4090 run Qwen3.5-27B?

44 words a second. 0.26 second wait. 19 of 20 coding answers worked. 18 GB used out of 24. The card runs this AI well - and it can hold a 128k window with 4 chats at the same time.

Read article >