(Modified:
2026-10-02)
— Written by
SimeonOnSecurity— 16 min read
Measured Ollama benchmarks of Llama 3.1 8B and Qwen3.8 27B across leading Vast.ai GPUs. Compare decode speed, long-context behavior, rental cost, self-hosting tradeoffs, API credits, and subscriptions.
(Modified:
2026-09-22)
— Written by
SimeonOnSecurity— 16 min read
Qwen3.8 27B and its ternary repack Bonsai 2 27B now outscore Claude Sonnet 4.6 on the aggregate intelligence index while running on one consumer GPU. What changed, what the benchmarks show, and why memory pricing makes waiting the most expensive option.
(Modified:
2026-09-20)
— Written by
SimeonOnSecurity— 19 min read
Use measured Raspberry Pi 4 and 5 results to choose local language models by memory, speed, and workload, from tiny LFM2.5 models to 3B and larger options.
(Modified:
2026-09-12)
— Written by
SimeonOnSecurity— 7 min read
A practical account of building a local AI assistant for Meshtastic, with private configuration, queued TCP access, retrieval tools, and a safer dashboard.
