GaⅤin.com by Gavin W.
Colibrì vs. FreeToken: Can Consumer Hardware Really Run Frontier MoE Models?
An empirical comparison of Colibri vs FreeToken for edge MoE serving, breaking down RAM limits, NVMe Direct DMA, the WSL2 I/O tax, and real tokens/sec.
hardware
Does Windows Dev Drive Actually Speed Up Local LLMs? A Deep Dive into ReFS, Defender, and NVMe Paging
Empirical benchmarks comparing Windows Dev Drive (ReFS) vs NTFS for local LLMs across cold TTFT, inference jitter, Colibri MoE streaming, and n-gram paging.
Getting 10 tok/s on Qwen 3.8 Flash Next: Why N-Gram Disk Paging Works Where MoE Fails
How I got Qwen 3.8 Flash Next running at 10 tokens/sec on an RTX 5060 Ti, and why paging n-gram tables from NVMe avoids the brutal disk bandwidth bottlenecks of MoE expert streaming.
Lessons in Troubleshooting: Blender: Not Enough Video Memory
Troubleshooting Blender startup crashes and "Not Enough Video Memory" errors caused by dual-monitor GPU display routing.
Selecting the Computer That’s Right for Me
Shopping for a computer can be overwhelming. Companies can bombard you with numbers and details in an attempt to get you to spend more money than you may need to for your needs. Knowing what these mean can save you money and frustration.