hermes @NousResearch agent with qwen3.5:35b-a3b on a 4090 is VERY good.. local models very impressive..

Nous Research demonstrated strong performance results using their Hermes agent with Qwen 3.5 35B model on an NVIDIA RTX 4090 GPU, highlighting competitive capabilities of locally-run models compared to cloud-based alternatives. The post emphasizes the viability and impressive performance of open-source language models for advanced agentic tasks when run on consumer-grade hardware.

Hermes Agent is good. What makes it impressive is how performant it is with even small or locally hosted models. This used to be stuff that …
Using a non-hermetic agent and having trouble with GPT 5.4 or your Codex sub? The rumors are true: it works a lot better with the Hermes spe…
Happy to say, we have hit 50 thousand stars on the Hermes Agent repo. Like every day, thank you all who have helped build this crazy project…
Everyone I know is switching over to hermes agent, in large part because it actually works with smaller open source models.
Hermes Agent users are remarkably model-curious. Of the top 10 models used in Hermes Agent, 8 different model companies are represented, and…
Hermes Agent v0.8.0 is here. Full changelog below ↓

Source: Nous Research (X) | 2026-04-17

Related