Instructions to use fesalfayed/gpt-oss-20b-hermes_agent-tool-finetune_gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use fesalfayed/gpt-oss-20b-hermes_agent-tool-finetune_gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="fesalfayed/gpt-oss-20b-hermes_agent-tool-finetune_gguf",
	filename="gpt-oss-20b-hermes.Q3_K_M.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use fesalfayed/gpt-oss-20b-hermes_agent-tool-finetune_gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf fesalfayed/gpt-oss-20b-hermes_agent-tool-finetune_gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf fesalfayed/gpt-oss-20b-hermes_agent-tool-finetune_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 fesalfayed/gpt-oss-20b-hermes_agent-tool-finetune_gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf fesalfayed/gpt-oss-20b-hermes_agent-tool-finetune_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 fesalfayed/gpt-oss-20b-hermes_agent-tool-finetune_gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf fesalfayed/gpt-oss-20b-hermes_agent-tool-finetune_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 fesalfayed/gpt-oss-20b-hermes_agent-tool-finetune_gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf fesalfayed/gpt-oss-20b-hermes_agent-tool-finetune_gguf:Q4_K_M

Use Docker

docker model run hf.co/fesalfayed/gpt-oss-20b-hermes_agent-tool-finetune_gguf:Q4_K_M

LM Studio
Jan

vLLM

How to use fesalfayed/gpt-oss-20b-hermes_agent-tool-finetune_gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "fesalfayed/gpt-oss-20b-hermes_agent-tool-finetune_gguf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "fesalfayed/gpt-oss-20b-hermes_agent-tool-finetune_gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/fesalfayed/gpt-oss-20b-hermes_agent-tool-finetune_gguf:Q4_K_M

Ollama
How to use fesalfayed/gpt-oss-20b-hermes_agent-tool-finetune_gguf with Ollama:
```
ollama run hf.co/fesalfayed/gpt-oss-20b-hermes_agent-tool-finetune_gguf:Q4_K_M
```

Unsloth Studio

How to use fesalfayed/gpt-oss-20b-hermes_agent-tool-finetune_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 fesalfayed/gpt-oss-20b-hermes_agent-tool-finetune_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 fesalfayed/gpt-oss-20b-hermes_agent-tool-finetune_gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for fesalfayed/gpt-oss-20b-hermes_agent-tool-finetune_gguf to start chatting

How to use fesalfayed/gpt-oss-20b-hermes_agent-tool-finetune_gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf fesalfayed/gpt-oss-20b-hermes_agent-tool-finetune_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": "fesalfayed/gpt-oss-20b-hermes_agent-tool-finetune_gguf:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use fesalfayed/gpt-oss-20b-hermes_agent-tool-finetune_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 fesalfayed/gpt-oss-20b-hermes_agent-tool-finetune_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 fesalfayed/gpt-oss-20b-hermes_agent-tool-finetune_gguf:Q4_K_M

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use fesalfayed/gpt-oss-20b-hermes_agent-tool-finetune_gguf with Docker Model Runner:
```
docker model run hf.co/fesalfayed/gpt-oss-20b-hermes_agent-tool-finetune_gguf:Q4_K_M
```

Lemonade

How to use fesalfayed/gpt-oss-20b-hermes_agent-tool-finetune_gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull fesalfayed/gpt-oss-20b-hermes_agent-tool-finetune_gguf:Q4_K_M

Run and chat with the model

lemonade run user.gpt-oss-20b-hermes_agent-tool-finetune_gguf-Q4_K_M

List all available models

lemonade list

gpt-oss-20b · Hermes-Agent tool finetune · GGUF

GGUF quants for llama.cpp, Ollama, and LM Studio. Five quants shipped — pick by RAM budget.

Format — GGUF
Quants shipped — Q3_K_M, Q4_K_M, Q5_K_M, Q8_0, F16
Recommended — Q4_K_M for 16 GB RAM, Q8_0 for quality
Runtime — llama.cpp, Ollama, LM Studio, koboldcpp

What this is

A tool-use finetune of OpenAI's gpt-oss-20b for Hermes-Agent, a local agent framework that needs models which call tools reliably, follow multi-turn instructions, and don't argue with system prompts.

The base model is the 21B-parameter (3.6B active) Mixture-of-Experts release from OpenAI. This finetune preserves the Harmony chat template and the reasoning-effort knob, and improves:

Function-calling adherence (correct JSON, no commentary mid-call)
Long agent loops (10+ turns of tool → observe → plan)
System-prompt fidelity (respects role boundaries and refusal/allow-list rules)

It is not affiliated with NousResearch's Hermes model series. "Hermes-Agent" here refers to the local agent framework only.

Files

Quant	Size	Use case
Q3_K_M	~10.0 GB	Tight RAM, lowest acceptable quality
Q4_K_M	~12.5 GB	Best quality / size trade-off (default)
Q5_K_M	~14.5 GB	Higher quality, modest size bump
Q8_0	~22 GB	Near-lossless
F16	~41 GB	Reference, no quantization

(Sizes are approximate; check the file list for exact bytes.)

Quickstart

llama.cpp

./llama-server \
  -hf fesalfayed/gpt-oss-20b-hermes_agent-tool-finetune_gguf:Q4_K_M \
  --port 1234 \
  -c 8192 \
  --jinja

Ollama

ollama run hf.co/fesalfayed/gpt-oss-20b-hermes_agent-tool-finetune_gguf:Q4_K_M

LM Studio

Search for fesalfayed/gpt-oss-20b-hermes_agent-tool-finetune_gguf in the Discover tab and pick a quant. Enable "Use Jinja chat template" in the model settings so Harmony renders correctly.

Hermes-Agent integration

Add a profile in ~/.hermes/config.yaml:

profiles:
  gpt-oss-20b-tools:
    provider: openai
    base_url: http://127.0.0.1:1234/v1   # LM Studio / vLLM / mlx_lm.server
    model: fesalfayed/gpt-oss-20b-hermes_agent-tool-finetune_gguf
    temperature: 0.7
    top_p: 0.95
    min_p: 0.1                            # important for MoE stability
    max_tokens: 8192
    tool_choice: auto

Then hermes profile use gpt-oss-20b-tools and the agent loop will route tool calls through this model.

Sampling

Param	Value	Why
temperature	0.7	balanced; drop to 0.2 for strict tool calls
top_p	0.95	standard nucleus
min_p	0.1	required for MoE — prevents dead-expert tokens
repetition_penalty	1.0	the model handles repetition itself

Harmony reasoning effort: set the system message to Reasoning: low|medium|high. high is roughly 3-4x more output tokens but noticeably better on multi-step tool plans.

Training

Base: openai/gpt-oss-20b
Method: LoRA SFT (rank 64, alpha 16) merged back into BF16
Frame: Unsloth + TRL on a single H100 (80 GB)
Data: ~42k tool-use traces from Hermes-Agent sessions, filtered for successful tool calls and clean JSON. No synthetic distillation.
Length: 8192 tokens, packing on
Loss: assistant-only, mask user/system/tool

The _16bit repo holds the merged BF16 weights. The _4bit, _mlx, and _gguf repos are quantizations of that checkpoint.

Limitations

Math and code-generation are unchanged from the base — this finetune optimizes the agent loop, not raw reasoning.
The model can over-call tools when given vague instructions. Add a "if you can answer directly, do so" line to the system prompt.
English only. Other languages were not in the training mix.
Not safety-tuned beyond what gpt-oss-20b already provides.

Other formats

BF16 reference — full precision, vLLM / Transformers
MXFP4 4-bit — fits a 16 GB GPU
MLX — Apple Silicon native
GGUF — llama.cpp / Ollama / LM Studio

License

Apache-2.0, inherited from the base model. No additional restrictions.

Citation

@misc{fesalfayed_gptoss20b_hermesagent_2025,
  author = {Fayed, Fesal},
  title  = {gpt-oss-20b Hermes-Agent tool finetune (gguf)},
  year   = {2025},
  url    = {https://huggingface.co/fesalfayed/gpt-oss-20b-hermes_agent-tool-finetune_gguf},
}

Downloads last month: 1,750

GGUF

Model size

21B params

Architecture

gpt-oss

Hardware compatibility

3-bit

4-bit

5-bit

8-bit

16-bit

Model tree for fesalfayed/gpt-oss-20b-hermes_agent-tool-finetune_gguf

Base model

openai/gpt-oss-20b

Quantized

(202)

this model

Collection including fesalfayed/gpt-oss-20b-hermes_agent-tool-finetune_gguf

finetuned_hermes-function-calling-v1

Collection

Models fine-tuned on Hermes tool calling dataset • 4 items • Updated May 2 • 1