Instructions to use DJLougen/Harmonic-Hermes-9B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DJLougen/Harmonic-Hermes-9B-GGUF with HERMES:

# No code snippets available yet for this library.

# To use this model, check the repository files and the library's documentation.

# Want to help? PRs adding snippets are welcome at:
# https://github.com/huggingface/huggingface.js

llama-cpp-python

How to use DJLougen/Harmonic-Hermes-9B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="DJLougen/Harmonic-Hermes-9B-GGUF",
	filename="Harmonic-Hermes-9B-BF16-mmproj.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use DJLougen/Harmonic-Hermes-9B-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf DJLougen/Harmonic-Hermes-9B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf DJLougen/Harmonic-Hermes-9B-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf DJLougen/Harmonic-Hermes-9B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf DJLougen/Harmonic-Hermes-9B-GGUF:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf DJLougen/Harmonic-Hermes-9B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf DJLougen/Harmonic-Hermes-9B-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf DJLougen/Harmonic-Hermes-9B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf DJLougen/Harmonic-Hermes-9B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/DJLougen/Harmonic-Hermes-9B-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use DJLougen/Harmonic-Hermes-9B-GGUF with Ollama:
```
ollama run hf.co/DJLougen/Harmonic-Hermes-9B-GGUF:Q4_K_M
```

Unsloth Studio

How to use DJLougen/Harmonic-Hermes-9B-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for DJLougen/Harmonic-Hermes-9B-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for DJLougen/Harmonic-Hermes-9B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for DJLougen/Harmonic-Hermes-9B-GGUF to start chatting

How to use DJLougen/Harmonic-Hermes-9B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf DJLougen/Harmonic-Hermes-9B-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "DJLougen/Harmonic-Hermes-9B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use DJLougen/Harmonic-Hermes-9B-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf DJLougen/Harmonic-Hermes-9B-GGUF:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default DJLougen/Harmonic-Hermes-9B-GGUF:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use DJLougen/Harmonic-Hermes-9B-GGUF with Docker Model Runner:
```
docker model run hf.co/DJLougen/Harmonic-Hermes-9B-GGUF:Q4_K_M
```

Lemonade

How to use DJLougen/Harmonic-Hermes-9B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull DJLougen/Harmonic-Hermes-9B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Harmonic-Hermes-9B-GGUF-Q4_K_M

List all available models

lemonade list

☕ Support This Work

I'm a PhD student in visual neuroscience at the University of Toronto who also happens to spend way too much time fine-tuning, merging, and quantizing open-weight models on rented H100s and a local DGX Spark. It's a hobby that got out of hand. If my uploads have been useful to you, consider buying a PhD student a coffee. It goes a long way toward keeping these experiments running.

☕ ko-fi.com/djlougen

Harmonic-Hermes-9B-GGUF

GGUF quantizations of Harmonic-Hermes-9B for local inference with llama.cpp, Ollama, LM Studio, and other GGUF-compatible runtimes.

Harmonic-Hermes-9B is the Stage 2 agentic fine-tune of Harmonic-9B — a dedicated tool-calling and agent model built on top of a strong reasoning backbone.

Where Harmonic-9B teaches the model how to think, Harmonic-Hermes-9B teaches it how to act — structured tool use, multi-turn agent workflows, and function calling, all grounded in the reasoning depth from Stage 1.

Stage 1 — Harmonic-9B: Heavy reasoning fine-tune on privately generated, structurally validated data. Every row passes strict quality gates. The thinking backbone.

Stage 2 (this model): Agentic fine-tune on hermes-agent-traces-filtered — 3,679 structurally validated agent traces with deep reasoning, tool calling, and multi-turn workflows.

Available Quantizations

File	Quant	Size	Use Case
`Qwen3.5-9B-Harmonic.F16.gguf`	F16	~18 GB	Maximum quality, needs 24GB+ VRAM
`Harmonic-Hermes-9B-Q8_0.gguf`	Q8_0	~9.5 GB	Near-lossless, 16GB VRAM
`Harmonic-Hermes-9B-Q6_K.gguf`	Q6_K	~6.9 GB	Very high quality, 12GB VRAM
`Harmonic-Hermes-9B-Q5_K_M.gguf`	Q5_K_M	~6.1 GB	Best 5-bit for quality
`Harmonic-Hermes-9B-Q5_K_S.gguf`	Q5_K_S	~5.9 GB	5-bit, smaller
`Harmonic-Hermes-9B-Q5_0.gguf`	Q5_0	~5.9 GB	5-bit legacy
`Qwen3.5-9B-Harmonic.Q4_K_M.gguf`	Q4_K_M	~5.3 GB	Best 4-bit for quality
`Harmonic-Hermes-9B-Q4_K_S.gguf`	Q4_K_S	~5.0 GB	4-bit, smaller
`Harmonic-Hermes-9B-Q4_0.gguf`	Q4_0	~5.0 GB	4-bit legacy
`Harmonic-Hermes-9B-IQ4_XS.gguf`	IQ4_XS	~4.9 GB	4-bit imatrix, smallest 4-bit
`Harmonic-Hermes-9B-Q3_K_L.gguf`	Q3_K_L	~4.6 GB	Best 3-bit for quality
`Harmonic-Hermes-9B-Q3_K_M.gguf`	Q3_K_M	~4.4 GB	3-bit, balanced
`Harmonic-Hermes-9B-Q3_K_S.gguf`	Q3_K_S	~4.0 GB	3-bit, smaller
`Harmonic-Hermes-9B-Q2_K.gguf`	Q2_K	~3.6 GB	Smallest, significant quality loss

MLX (Apple Silicon)

MLX conversions are available in separate repos:

Repo	Quant	Size
Harmonic-Hermes-9B-MLX-bf16	BF16	~17 GB
Harmonic-Hermes-9B-MLX-8bit	8-bit	~8.9 GB
Harmonic-Hermes-9B-MLX-4bit	4-bit	~4.8 GB

Vision (Multimodal)

This model includes vision projectors for multimodal inference. Use with llama.cpp's --mmproj flag for image understanding tasks.

How Our Training Data Compares

Quality Comparison

Metrics Summary

We ran the same structural quality analysis used for Stage 1 against comparable public agentic datasets. The results show why starting from quality-filtered data matters:

Metric	Harmonic Traces (ours)	Carnice GLM-5 (kai-os)
Rows	3,679	1,627
Source model	Multiple frontier models	GLM-5 via OpenRouter
Think block depth	581 words avg	40 words avg
Self-correction	63.0%	29.7%
Verification	95.9%	63.7%
Alternative exploration	43.7%	51.3%
Valid JSON (all tool calls)	100%	100%
Tool calls per conversation	18.5	5.4
Messages per conversation	32.1	12.1
Multi-turn (>5 messages)	97.8%	89.6%

The critical gap is reasoning depth: 581 vs 40 words in think blocks. Carnice traces plan briefly then act — the model learns tool-call formatting but not deliberation. Our traces contain 14x deeper reasoning before every action, with nearly universal verification (96% vs 64%) and twice the self-correction rate.

The conversation depth also matters for agent training. Our traces average 32 messages and 18 tool calls per trajectory — complete agentic sessions, not short dispatches. This teaches the model to maintain coherent state across extended multi-step workflows.

Reasoning Flow

Marker density across thinking traces — the filtered set shows tighter, more consistent reasoning structure.

Conversation Structure

Category Distribution

Training data: DJLougen/hermes-agent-traces-filtered

What This Model Does

Tool calling / function calling — structured JSON tool use in the Hermes agent format
Multi-turn agent workflows — maintains coherent state across extended tool-use conversations
Reasoning-grounded decisions — inherits Harmonic-9B's self-correction, verification, and exploration before committing to actions

Training Approach

Harmonic-Hermes-9B is a Stage 2 fine-tune of Harmonic-9B, trained on hermes-agent-traces-filtered — 3,679 structurally validated agent traces with deep reasoning, tool calling, and multi-turn workflows.

The key insight: most agent models are fine-tuned directly from base models or generic instruct tunes. They learn tool-call formatting but not when or why to use tools. By starting from a model that already reasons deeply (Stage 1), the agent behaviors are grounded in genuine multi-step thinking rather than pattern-matched tool invocations.

Usage

Ollama

ollama run DJLougen/Harmonic-Hermes-9B-GGUF

llama.cpp

./llama-cli -m Harmonic-Hermes-9B-Q8_0.gguf -p "Use the available tools to..." -n 4096

LM Studio

Download any quantization and load in LM Studio. The model follows standard ChatML formatting.

Reasoning + Tool Use

The model uses <think> blocks for reasoning before acting:

<think>
The user wants to check the weather in Toronto. I have a get_weather tool available.
Let me call it with the right parameters...
</think>

<tool_call>
{"name": "get_weather", "arguments": {"location": "Toronto, Canada"}}
</tool_call>

Intended Use

Agentic workflows with tool calling and function execution
Multi-turn assistant interactions requiring structured reasoning
Local inference as an always-on agent backbone
Research into reasoning-grounded agent behavior

Limitations

9B parameter model — not suitable for tasks requiring extensive world knowledge
Agent capabilities are shaped by the training data distribution
Benchmark evaluation is ongoing

Architecture

Base: Harmonic-9B (Stage 1 reasoning fine-tune of Qwen 3.5 9B)
Parameters: 9.65B
Training: LoRA fine-tuning, merged into base weights
Precision: BF16
Context: 8192 tokens

License

Apache 2.0 — same as the base model. Fully commercial use permitted.

Dataset used to train DJLougen/Harmonic-Hermes-9B-GGUF

Collection including DJLougen/Harmonic-Hermes-9B-GGUF

Harmonic

Collection

Harmonic series post-trained models. • 4 items • Updated 11 days ago

DJLougen
/

Harmonic-Hermes-9B-GGUF

☕ Support This Work

Harmonic-Hermes-9B-GGUF

Available Quantizations

MLX (Apple Silicon)

Vision (Multimodal)

How Our Training Data Compares

Quality Comparison

Metrics Summary

Reasoning Flow

Conversation Structure

Category Distribution

What This Model Does

Training Approach

Usage

Ollama

llama.cpp

LM Studio

Reasoning + Tool Use

Intended Use

Limitations

Architecture

License

Links

Dataset used to train DJLougen/Harmonic-Hermes-9B-GGUF

Collection including DJLougen/Harmonic-Hermes-9B-GGUF

Harmonic