Instructions to use RegalInvader/Marco-Nano-Instruct-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use RegalInvader/Marco-Nano-Instruct-GGUF 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 RegalInvader/Marco-Nano-Instruct-GGUF:TQ1_0
# Run inference directly in the terminal:
llama cli -hf RegalInvader/Marco-Nano-Instruct-GGUF:TQ1_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf RegalInvader/Marco-Nano-Instruct-GGUF:TQ1_0
# Run inference directly in the terminal:
llama cli -hf RegalInvader/Marco-Nano-Instruct-GGUF:TQ1_0

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf RegalInvader/Marco-Nano-Instruct-GGUF:TQ1_0
# Run inference directly in the terminal:
./build/bin/llama cli -hf RegalInvader/Marco-Nano-Instruct-GGUF:TQ1_0

Use Docker

docker model run hf.co/RegalInvader/Marco-Nano-Instruct-GGUF:TQ1_0

Llama new
LM Studio
Jan

vLLM

How to use RegalInvader/Marco-Nano-Instruct-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RegalInvader/Marco-Nano-Instruct-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": "RegalInvader/Marco-Nano-Instruct-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/RegalInvader/Marco-Nano-Instruct-GGUF:TQ1_0

Ollama
How to use RegalInvader/Marco-Nano-Instruct-GGUF with Ollama:
```
ollama run hf.co/RegalInvader/Marco-Nano-Instruct-GGUF:TQ1_0
```
Unsloth Desktop

How to use RegalInvader/Marco-Nano-Instruct-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf RegalInvader/Marco-Nano-Instruct-GGUF:TQ1_0

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "RegalInvader/Marco-Nano-Instruct-GGUF:TQ1_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use RegalInvader/Marco-Nano-Instruct-GGUF with Docker Model Runner:
```
docker model run hf.co/RegalInvader/Marco-Nano-Instruct-GGUF:TQ1_0
```

Lemonade

How to use RegalInvader/Marco-Nano-Instruct-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull RegalInvader/Marco-Nano-Instruct-GGUF:TQ1_0

Run and chat with the model

lemonade run user.Marco-Nano-Instruct-GGUF-TQ1_0

List all available models

lemonade list

Hermes Agent

How to use RegalInvader/Marco-Nano-Instruct-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf RegalInvader/Marco-Nano-Instruct-GGUF:TQ1_0

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 RegalInvader/Marco-Nano-Instruct-GGUF:TQ1_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use RegalInvader/Marco-Nano-Instruct-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf RegalInvader/Marco-Nano-Instruct-GGUF:TQ1_0

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "RegalInvader/Marco-Nano-Instruct-GGUF:TQ1_0" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Marco-Nano-Instruct-GGUF / code /tests /test_gguf.py

RegalInvader

Release: Marco-Nano-Instruct 1-, 2- and 3-bit GGUF for phones

e5235fb verified 4 days ago

Raw History Blame Contribute Delete

1.48 kB

"""GGUF export (T2.7): tensor types of a student export, with the dense matrices as trained (bf16) or Q8_0."""
import sys
from pathlib import Path

import numpy as np
import pytest
import torch

from lowbit.export import gguf as gx

GGUF_PY = Path("/path/to/llama.cpp/gguf-py")
pytestmark = pytest.mark.skipif(not GGUF_PY.exists(), reason="llama.cpp's gguf-py is not on this machine")


def test_dense_as_q8_0_quantises_matrices_only():
    sys.path.insert(0, str(GGUF_PY))
    import gguf
    T = gguf.GGMLQuantizationType
    torch.manual_seed(0)
    dense = {"model.layers.0.self_attn.q_proj.weight": torch.randn(64, 128, dtype=torch.bfloat16),
             "model.layers.0.input_layernorm.weight": torch.ones(128),
             "model.layers.0.mlp.gate.weight": torch.randn(8, 128),
             "model.embed_tokens.weight": torch.randn(32, 128, dtype=torch.bfloat16)}
    plain = gx.student_tensors(dense, {}, gguf)
    q8 = gx.student_tensors(dense, {}, gguf, dense_as="q8_0")
    assert plain["blk.0.attn_q.weight"][0] == T.BF16 and q8["blk.0.attn_q.weight"][0] == T.Q8_0
    assert q8["token_embd.weight"][0] == T.Q8_0
    assert q8["blk.0.attn_norm.weight"][0] == T.F32 and q8["blk.0.ffn_gate_inp.weight"][0] == T.F32  # norms, router
    back = gguf.quants.dequantize(q8["blk.0.attn_q.weight"][1], T.Q8_0)
    ref = dense["model.layers.0.self_attn.q_proj.weight"].float().numpy()
    assert back.shape == ref.shape and np.abs(back - ref).max() < 0.02 * np.abs(ref).max()

	"""GGUF export (T2.7): tensor types of a student export, with the dense matrices as trained (bf16) or Q8_0."""
	import sys
	from pathlib import Path

	import numpy as np
	import pytest
	import torch

	from lowbit.export import gguf as gx

	GGUF_PY = Path("/path/to/llama.cpp/gguf-py")
	pytestmark = pytest.mark.skipif(not GGUF_PY.exists(), reason="llama.cpp's gguf-py is not on this machine")


	def test_dense_as_q8_0_quantises_matrices_only():
	sys.path.insert(0, str(GGUF_PY))
	import gguf
	T = gguf.GGMLQuantizationType
	torch.manual_seed(0)
	dense = {"model.layers.0.self_attn.q_proj.weight": torch.randn(64, 128, dtype=torch.bfloat16),
	"model.layers.0.input_layernorm.weight": torch.ones(128),
	"model.layers.0.mlp.gate.weight": torch.randn(8, 128),
	"model.embed_tokens.weight": torch.randn(32, 128, dtype=torch.bfloat16)}
	plain = gx.student_tensors(dense, {}, gguf)
	q8 = gx.student_tensors(dense, {}, gguf, dense_as="q8_0")
	assert plain["blk.0.attn_q.weight"][0] == T.BF16 and q8["blk.0.attn_q.weight"][0] == T.Q8_0
	assert q8["token_embd.weight"][0] == T.Q8_0
	assert q8["blk.0.attn_norm.weight"][0] == T.F32 and q8["blk.0.ffn_gate_inp.weight"][0] == T.F32 # norms, router
	back = gguf.quants.dequantize(q8["blk.0.attn_q.weight"][1], T.Q8_0)
	ref = dense["model.layers.0.self_attn.q_proj.weight"].float().numpy()
	assert back.shape == ref.shape and np.abs(back - ref).max() < 0.02 * np.abs(ref).max()