Install Ollama
Download and run OllamaSetup.exe from ollama.com/download, or paste this into PowerShell. Ollama starts in the background and adds an icon to the taskbar. Use version 0.40.16 or newer.
Download OllamaConnect Hermes Agent to AtomicChat’s LFM3-1.7B Uncensored through Ollama on Windows, Mac or Linux and have it read two files and write a review. An experiment with a very small model.
Estimated from the published file sizes plus runtime and context headroom at 65,536 tokens. Not measured by YouRunAI.
| Machine | AD-Q4_K_M · 1.13 GB | AD-Q6_K · 1.59 GB |
|---|---|---|
| Windows or Linux PC · CPU · 8 GB RAM | Should load; each Hermes turn is slow because the agent sends a long tool prompt | Prefer Q4 on 8 GB |
| Windows or Linux PC · CPU · 16 GB RAM | Recommended start | Fits |
| Apple Silicon Mac · 8 GB unified memory | Should load with other apps closed | Prefer Q4 on 8 GB |
| Apple Silicon Mac · 16 GB unified memory | Recommended Mac start | Fits |
| Any PC with a 6 GB or larger GPU | Fits on the GPU; faster prompt processing | Fits on the GPU |
Hermes Agent is desktop software, so this guide covers Windows, Mac and Linux computers. Running the agent on a phone is not covered here.
Pull the 1.13 GB GGUF into Ollama on your computer, connect Hermes with Ollama’s launcher, and have the agent read two project files and write review.md. You approve each file action. Hermes runs on a computer; to use this model on a phone, follow the phone chat guide on the model page.
Select the weights you want. The instructions, downloads and settings change with your choice.
The publisher has not provided a complete memory target for this task. Check its hardware guidance before starting.
The 1.13 GB file is only the weights; a 65,536-token agent context adds memory on top. 16 GB of system or unified memory is the comfortable estimate. Not a YouRunAI measurement.
Choose where you want to run it. The instructions below update to match your selection.
Download and run OllamaSetup.exe from ollama.com/download, or paste this into PowerShell. Ollama starts in the background and adds an icon to the taskbar. Use version 0.40.16 or newer.
Download OllamaHermes needs a long context, and Ollama starts most models at 4,096 tokens on GPUs under 24 GB. Open Ollama’s Settings from its taskbar icon and move the Context length slider to 64k. That is the only setting you change.
Ollama context lengthIn PowerShell, run this to download AtomicChat’s 1.13 GB file straight from Hugging Face.
Exact file on Hugging FaceHermes Desktop is Nous Research’s free app for Hermes, with a chat window, file browser and tool output, so you do not need the terminal. Run this command: Ollama installs Hermes Desktop if you do not have it, connects it to LFM3-1.7B Uncensored and opens the app. You can also download the app first from the Hermes Desktop page (Windows 10 or 11). The app uses the model you launch it with: to switch to another model later, run the same command with that model’s name. If the model is not listed in the app, run ollama list to check that the download finished.
Download Hermes Desktop Ollama’s Hermes Desktop integration Hermes Desktop guidePrefer the terminal? Run this instead. It installs the Hermes command-line agent if needed and opens a Hermes chat in this window; it shares settings, sessions and memory with the desktop app. Skip the optional messaging setup. If you see “Hermes Gateway Starting…” instead of a chat, press Ctrl+C and run hermes.
Ollama’s Hermes integration Hermes Agent installation (manual option)In the Hermes chat (the desktop app or the terminal), paste the task below. It has Hermes create a notes file, read it back and write a review, so you can see it use real file tools. Hermes asks before each file action; read each request and approve it. A model with reduced refusals will not push back on risky actions, so keep these approvals on.
| Setting | Value |
|---|---|
| Task to paste into Hermes | Create a folder named agent-test. Inside it, write notes.md saying: launch day is Thursday 14 May, the owner is Priya, and the database migration runs at 09:00 before the app deploy. Then read notes.md and write review.md with a numbered launch checklist that adds a verified database backup before the migration, plus one sentence on the risk of skipping it. |
Open the agent-test folder. review.md should name Thursday 14 May and Priya and put a backup step before the migration. If both files exist, the agent is reading and writing files on your computer. Next time, open the Hermes Desktop app, or run hermes in a terminal (type /exit to leave).
review.md names the launch day and owner from notes.md, adds a verified backup before the migration, and Hermes’ activity shows the file reads and one approved write.
Read this before you start: Liquid AI cautions against multi-step agentic work with the 1.7B base model, and neither AtomicChat nor YouRunAI has tested this file with Hermes. Treat it as an experiment. If it cannot complete the task, the larger models in this series are the reliable agent choices. Sources checked November 17, 2026; hardware ratings are estimates.
Run ollama ps while Hermes is working: the CONTEXT column should say 65536. If it says 4096, the context slider (or the Linux setting) did not apply; set it again and restart Ollama. If Hermes still answers only in chat, update Ollama and try the larger package if there is one.
Update Ollama to 0.40.16 or newer (re-run the installer, or Check for Updates from its icon), restart it, and run the command again. ollama pull resumes an interrupted download.
Choose a smaller package if there is one, or move Ollama’s context slider down to 32k. If it runs out of memory as soon as Hermes starts, run hermes config set model.context_length 65536 so Hermes does not ask for the model’s full maximum context.
This is the expected limit of a 1.7B model. Start a new Hermes session and retry once, then try the AD-Q6_K package. If it still fails, use a larger model for agent work and keep this one for chat.
Close and reopen the terminal. Follow any PATH or dependency message the installer printed.
Original instructions, model files, and compatibility notes behind this setup.
Source-backed package and platform-route plan for private local chat with Qwen3.5 · 9B. Preserves the official Ollama 9B package, a smaller 4B family fallback, and a clearly labeled community uncensored GGUF option.
Run Qwen3.8 27B with Ollama, connect it to Cline in VS Code, and make one reviewable code change in a tiny local project.
Generate images from text prompts in ComfyUI with the fast distilled or more adjustable base 4B model. Save your results and reuse the visual workflow.