Instructions to use cafonez/Agent-Nemotron-ROCmFP6 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cafonez/Agent-Nemotron-ROCmFP6 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="cafonez/Agent-Nemotron-ROCmFP6",
	filename="Nemotron-3-Nano-30B-A3B-Q6_0_ROCMFPX_AGENT-00001-of-00002.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 cafonez/Agent-Nemotron-ROCmFP6 with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf cafonez/Agent-Nemotron-ROCmFP6
# Run inference directly in the terminal:
llama cli -hf cafonez/Agent-Nemotron-ROCmFP6

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf cafonez/Agent-Nemotron-ROCmFP6
# Run inference directly in the terminal:
llama cli -hf cafonez/Agent-Nemotron-ROCmFP6

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 cafonez/Agent-Nemotron-ROCmFP6
# Run inference directly in the terminal:
./llama-cli -hf cafonez/Agent-Nemotron-ROCmFP6

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 cafonez/Agent-Nemotron-ROCmFP6
# Run inference directly in the terminal:
./build/bin/llama-cli -hf cafonez/Agent-Nemotron-ROCmFP6

Use Docker

docker model run hf.co/cafonez/Agent-Nemotron-ROCmFP6

LM Studio
Jan

vLLM

How to use cafonez/Agent-Nemotron-ROCmFP6 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cafonez/Agent-Nemotron-ROCmFP6"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cafonez/Agent-Nemotron-ROCmFP6",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/cafonez/Agent-Nemotron-ROCmFP6

Ollama
How to use cafonez/Agent-Nemotron-ROCmFP6 with Ollama:
```
ollama run hf.co/cafonez/Agent-Nemotron-ROCmFP6
```

Unsloth Studio

How to use cafonez/Agent-Nemotron-ROCmFP6 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 cafonez/Agent-Nemotron-ROCmFP6 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 cafonez/Agent-Nemotron-ROCmFP6 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for cafonez/Agent-Nemotron-ROCmFP6 to start chatting

How to use cafonez/Agent-Nemotron-ROCmFP6 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf cafonez/Agent-Nemotron-ROCmFP6

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": "cafonez/Agent-Nemotron-ROCmFP6"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use cafonez/Agent-Nemotron-ROCmFP6 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf cafonez/Agent-Nemotron-ROCmFP6

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 cafonez/Agent-Nemotron-ROCmFP6

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use cafonez/Agent-Nemotron-ROCmFP6 with Docker Model Runner:
```
docker model run hf.co/cafonez/Agent-Nemotron-ROCmFP6
```

Lemonade

How to use cafonez/Agent-Nemotron-ROCmFP6 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull cafonez/Agent-Nemotron-ROCmFP6

Run and chat with the model

lemonade run user.Agent-Nemotron-ROCmFP6-{{QUANT_TAG}}

List all available models

lemonade list

Agent-Nemotron-ROCmFP6 / README.md

cafonez

Update README.md

1e4a324 verified 11 days ago

preview code

Raw

History Blame Contribute Delete

3.49 kB

	---
	base_model: nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
	license: other
	license_name: nvidia-nemotron-open-model-license
	license_link: https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-nemotron-open-model-license/
	tags:
	- gguf
	- quantized
	- rocm
	- rocmfpx
	- agentic
	- tool-calling
	- nemotron
	- nemotron-3
	- nvidia
	- text-generation
	- llama.cpp
	---

	# Agent-Nemotron-ROCmFP6

	Q6_0_ROCMFPX_AGENT (ROCmFP6 Agent) quantized GGUF of NVIDIA's Nemotron-3-Nano-30B-A3B.

	- Base model: [nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16](https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16)
	- Quantization: `Q6_0_ROCMFPX_AGENT` — ROCm-optimized 6-bit format with agent/tool-call coherent routing
	- Size: ~27.4 GiB (21 GB + 6.4 GB shards)
	- Parameters: ~30B total / 3.5B active (hybrid Mamba-2 + MoE)
	- Optimized for: Agentic workflows, tool calling, reasoning on AMD ROCm and Vulkan backends

	This quantization uses custom ROCmFPX kernels (part of experimental ROCmFPx family in llama.cpp) that provide better performance/quality on ROCm hardware for agent-style workloads. The `_AGENT` preset protects and enhances routing for tool use (Hermes-style / OpenClaw / BFCL etc.).



	## Files

	\| File \| Size \| Description \|
	\|------\|------\|-------------\|
	\| `Nemotron-3-Nano-30B-A3B-Q6_0_ROCMFPX_AGENT-00001-of-00002.gguf` \| 21 GB \| Main weights shard \|
	\| `Nemotron-3-Nano-30B-A3B-Q6_0_ROCMFPX_AGENT-00002-of-00002.gguf` \| 6.4 GB \| Second shard \|

	## Recommended Usage (llama.cpp)

	Use a ROCmFPX-enabled build of llama.cpp (see ROCmFPX projects / strix builds).

	### Quick server (recommended flags)

	```bash
	# Using the convenience wrapper (if installed)
	HERMES_NEMOTRON_NANO_FP6_MODEL=/path/to/Nemotron-3-Nano-30B-A3B-Q6_0_ROCMFPX_AGENT-00001-of-00002.gguf \
	hermes-nemotron-nano-30b-rocmfp6-agent-server
	```

	Direct `llama-server`:

	```bash
	llama-server \
	-m /path/to/Nemotron-3-Nano-30B-A3B-Q6_0_ROCMFPX_AGENT-00001-of-00002.gguf \
	--alias nemotron-nano-30b-rocmfp6-agent \
	--host 0.0.0.0 --port 8101 \
	-dev ROCm0 \
	-ngl 999 \
	-fa on \
	--mmap \
	--jinja \
	-c 131072 \
	-b 512 -ub 512 \
	--reasoning off \
	--slots \
	--metrics
	```

	For best agent/tool performance use `--jinja` (the GGUF embeds a strong Nemotron tool calling template).

	### Key notes

	- `Q6_0_ROCMFPX_AGENT` spends a few extra bits on agent routing tensors compared to plain `Q6_0_ROCMFPX`.
	- Excellent balance of quality vs size for agentic use on high-end AMD GPUs (Strix Halo, etc.).
	- Supports very long context (tested high values).
	- Tool calling format is the Nemotron `<tool_call>` style (also compatible with many frameworks via parsers).

	## Chat Template

	The GGUF includes the official Nemotron-3 tool-aware chat template. Use `--jinja` (or equivalent) with your loader.

	## Benchmarks (example from development)

	Typical token/s on ROCm0 (full offload) for this quant:
	- ~650+ t/s prompt eval (pp512)
	- ~53 t/s generation (tg128)

	Results vary by hardware + context.

	## License

	- Original weights: [NVIDIA Nemotron Open Model License](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-nemotron-open-model-license/)
	- This is a derived quantized artifact. You must comply with the base model's license terms.

	---

	Model page: https://huggingface.co/cafonez/Agent-Nemotron-ROCmFP6

	For questions or issues with the quantization, refer to the ROCmFPX documentation in the corresponding development repositories.