@sudoingX: this is a laptop running a 31b parameter model at 99% gpu autonomously through hermes agent, 15 tok/s sustained, 22.8 o…
Summary
A 31B parameter model runs locally on a laptop via Hermes agent at 15 tok/s, using 22.8 GB VRAM and 94 W power, highlighting fully autonomous, private AI inference without cloud dependencies.
View Cached Full Text
Cached at: 04/21/26, 10:00 AM
this is a laptop running a 31b parameter model at 99% gpu autonomously through hermes agent, 15 tok/s sustained, 22.8 of 24gb vram gone, 94 watts at 50c. no api keys. no rate limits. no “your prompts are being used for training”. no monthly subscription. no anthropic telling me
Similar Articles
@analogalok: my 8 GB VRAM gaming laptop is absolutely going to hate me for this. but I still did it. ran a 31b dense model (Gemma 4 …
User runs Gemma 4 31B dense model on 8GB VRAM gaming laptop at ~3 tokens/sec using llama.cpp with MTP speculative decoding, demonstrating feasibility of running a 31B dense model on consumer hardware and proposing agentic workflows where a fast MoE model routes to this slower dense model for hard tasks.
@analogalok: I just got Gemma 4 26B A4B MoE model running fully locally with Hermes agent on an 8GB RTX 4060 and it's now backtestin…
A developer demonstrates running Gemma 4 26B MoE model locally on an 8GB RTX 4060 with Hermes agent to fully automate backtesting of trading strategies, highlighting the growing capability of local LLMs as autonomous agents.
@itsolelehmann: The best model setups to run on Hermes (by price tier): 1. If you have infinite budget: Go with GPT 5.5 or Claude Opus …
This post outlines budget-tiered AI model configurations for the Hermes application, recommending premium options like GPT 5.5 and Claude Opus 4.7 for unlimited budgets, cost-effective fallbacks like DeepSeek V4 Flash for tighter budgets, and local deployment via Qwen 3.6 for zero-cost inference.
Someone just ran a 744B parameter model at 30 tok/s across 6 consumer GPUs in 6 different US states over the open internet
A researcher debuted Shard, achieving 30 tok/s inference on a 744B parameter model distributed across 6 consumer GPUs over the open internet, a 15-20x improvement over previous methods.
@sudoingX: spent the last hour just enjoying this, and i have to say it: the Hermes Agent dashboard is beautiful. NousResearch shi…
A user praises the Hermes Agent dashboard from NousResearch, highlighting its clean UI and local agentic stack running a 35B MoE model (Ornith) at FP8 on a single DGX Spark.