✕ Clear all filters
4 articles
▶ Videos →

📰 Dev.to · Ian L. Paterson

4 articles · Updated every 3 hours · View all reads

All Articles 128,708Blog Posts 133,462Tech Tutorials 33,276Research Papers 25,143News 18,235 ⚡ AI Lessons
Building llama.cpp from source on a Dell Precision T5820 with an RTX 3090 Ti (after seven power cycles)
Dev.to · Ian L. Paterson 💻 AI-Assisted Coding ⚡ AI Lesson 2mo ago
Building llama.cpp from source on a Dell Precision T5820 with an RTX 3090 Ti (after seven power cycles)
I pulled a Quadro M4000 out of a used Dell Precision T5820, dropped in an RTX 3090 Ti, and turned the...
View lesson → + Playlist
Three Months of Speed-Up Experiments on a 3090 Ti: Autoregressive DFlash MTP for Qwen3.6-27B
Dev.to · Ian L. Paterson 🤖 AI Agents & Automation ⚡ AI Lesson 2mo ago
Three Months of Speed-Up Experiments on a 3090 Ti: Autoregressive DFlash MTP for Qwen3.6-27B
The setup The starting line was 43 tokens per second decode on vanilla llama.cpp. The...
View lesson → + Playlist
LLM Benchmark Rankings 2026: 15 Models Tested on 38 Real Coding Tasks
Dev.to · Ian L. Paterson 🧠 Large Language Models ⚡ AI Lesson 2mo ago
LLM Benchmark Rankings 2026: 15 Models Tested on 38 Real Coding Tasks
Most LLM benchmarks measure raw intelligence. Real deployment decisions also depend on latency,...
View lesson → + Playlist
Inference Arbitrage: How I Route 200+ Daily LLM Calls Across Five Models
Dev.to · Ian L. Paterson 🧠 Large Language Models ⚡ AI Lesson 2mo ago
Inference Arbitrage: How I Route 200+ Daily LLM Calls Across Five Models
Inference arbitrage means routing each AI task to the cheapest model that can handle it at acceptable...
View lesson → + Playlist