5 articles
How much VRAM a local LLM needs: Q4 weights are about 30% of BF16, plus a KV cache that grows per token. Real numbers from 8 GB to 256 GB.
llmspeed estimates tokens per second for 30 machines and 15 models. What its numbers mean, the memory-bandwidth rule behind them, and why prefill matters for coding agents.
RTX Spark laptops ship October 16 with up to 128 GB of unified memory. Why the 600 GB/s figure is not memory bandwidth and which local coding models fit.
Flipper Zero firmware reaches stable 1.0 and moves to a community contribution model. What changes for contributors and how HN sees official vs custom firmware.
jamesob's local LLM guide: the $2k and $40k hardware paths, the BIOS and kernel settings that matter, and why multi-GPU setups fail at PCIe and IOMMU.
Showing 4 of 4 articles
New tutorials, open-source projects, and deep dives on coding agents - delivered weekly.
Explore 838 topics
Browse All Topics