https://localagentboard.com/news/ Which local models actually work with Hermes Agent, tested on real hardware. en https://localagentboard.com/news/best-local-llm-for-hermes-agent-top-picks/ https://localagentboard.com/news/best-local-llm-for-hermes-agent-top-picks/ Sun, 25 Oct 2026 00:00:00 GMT Which local model should you run Hermes Agent on? Measured picks from 16 tested setups on a DGX Spark: best overall, fastest reliable and best for 16–24 GB machines, with scores, speed and memory. https://localagentboard.com/news/hermes-agent-v0-22-5-retest-local-models/ https://localagentboard.com/news/hermes-agent-v0-22-5-retest-local-models/ Sun, 25 Oct 2026 00:00:00 GMT We reran our llama.cpp setups on Hermes Agent v0.22.5. Most scores moved by 2 points or less, within normal noise. Old vs new scores for every setup, and which ones are under review. https://localagentboard.com/news/localagentboard-launch-local-hermes-agent-leaderboard/ https://localagentboard.com/news/localagentboard-launch-local-hermes-agent-leaderboard/ Sun, 25 Oct 2026 00:00:00 GMT LocalAgentBoard is an independent leaderboard that tests which local LLMs, quants and engines actually complete Hermes Agent tasks, measured on an NVIDIA DGX Spark. 16 setups tested so far. https://localagentboard.com/news/q4-vs-q8-quantization-local-agent-benchmark/ https://localagentboard.com/news/q4-vs-q8-quantization-local-agent-benchmark/ Sun, 25 Oct 2026 00:00:00 GMT We tested Gemma 4 26B, Qwen3.6-35B-A3B and Nemotron-Cascade-2-30B at Q4, Q6 and Q8 on the same Hermes Agent tasks. Q4 scored within noise of Q8 while using much less memory and running faster. https://localagentboard.com/news/why-2-points-is-a-tie-local-llm-agent-benchmark/ https://localagentboard.com/news/why-2-points-is-a-tie-local-llm-agent-benchmark/ Sun, 25 Oct 2026 00:00:00 GMT The same local model can score 27, 30 and 28 out of 30 on identical agent tasks. Why LocalAgentBoard treats gaps of 2 points or less as a tie, and why Best overall is picked by speed within the top group.