Instructions to use Myric/Laguna-S-2.1-APEX-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Myric/Laguna-S-2.1-APEX-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Myric/Laguna-S-2.1-APEX-GGUF",
	filename="Laguna-S-2.1-APEX-i-compact.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 Myric/Laguna-S-2.1-APEX-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 Myric/Laguna-S-2.1-APEX-GGUF:Q8_0
# Run inference directly in the terminal:
llama cli -hf Myric/Laguna-S-2.1-APEX-GGUF:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Myric/Laguna-S-2.1-APEX-GGUF:Q8_0
# Run inference directly in the terminal:
llama cli -hf Myric/Laguna-S-2.1-APEX-GGUF:Q8_0

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 Myric/Laguna-S-2.1-APEX-GGUF:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf Myric/Laguna-S-2.1-APEX-GGUF:Q8_0

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 Myric/Laguna-S-2.1-APEX-GGUF:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Myric/Laguna-S-2.1-APEX-GGUF:Q8_0

Use Docker

docker model run hf.co/Myric/Laguna-S-2.1-APEX-GGUF:Q8_0

LM Studio
Jan

vLLM

How to use Myric/Laguna-S-2.1-APEX-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Myric/Laguna-S-2.1-APEX-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": "Myric/Laguna-S-2.1-APEX-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Myric/Laguna-S-2.1-APEX-GGUF:Q8_0

Ollama
How to use Myric/Laguna-S-2.1-APEX-GGUF with Ollama:
```
ollama run hf.co/Myric/Laguna-S-2.1-APEX-GGUF:Q8_0
```

Unsloth Studio

How to use Myric/Laguna-S-2.1-APEX-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 Myric/Laguna-S-2.1-APEX-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 Myric/Laguna-S-2.1-APEX-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Myric/Laguna-S-2.1-APEX-GGUF to start chatting

How to use Myric/Laguna-S-2.1-APEX-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Myric/Laguna-S-2.1-APEX-GGUF:Q8_0

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": "Myric/Laguna-S-2.1-APEX-GGUF:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Myric/Laguna-S-2.1-APEX-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 Myric/Laguna-S-2.1-APEX-GGUF:Q8_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 Myric/Laguna-S-2.1-APEX-GGUF:Q8_0

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use Myric/Laguna-S-2.1-APEX-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Myric/Laguna-S-2.1-APEX-GGUF:Q8_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 "Myric/Laguna-S-2.1-APEX-GGUF:Q8_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"

Docker Model Runner
How to use Myric/Laguna-S-2.1-APEX-GGUF with Docker Model Runner:
```
docker model run hf.co/Myric/Laguna-S-2.1-APEX-GGUF:Q8_0
```

Lemonade

How to use Myric/Laguna-S-2.1-APEX-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Myric/Laguna-S-2.1-APEX-GGUF:Q8_0

Run and chat with the model

lemonade run user.Laguna-S-2.1-APEX-GGUF-Q8_0

List all available models

lemonade list

Quant review-ish (Apex-I-Compact & Apex-I-Mini) for agentic coding (on rtx 5070+5700x3d+56gb ram)

by sanjxz - opened 6 days ago

Discussion

sanjxz

6 days ago

I tried this model with iq3_m-code quant from atomic chat and was very disappointed in how it run. it looped, didnt compact, didnt follow instructions mid turn, and so on.

then i tried apex-i-mini, which was a very noticeable step up - loops gone, but it still didnt compact (stuck at 95%) and sometimes ignored instructions. Speeds:
- barely usable outputs/for desperate.

so i downloaded apex-i-compact and now we are talking - no issues with model at all, everything works as expected, follows steering, no loops, even at q8\q5_1 kv (apex mini was at q8\q8) - and its faster in tg by about 1-2 t/s // i also added dry sampling params with this, maybe i-mini would benefit from them too.

Speeds:

Template used: https://huggingface.co/sanjxz/Laguna-S-2.1-Agentic-Chat-Template-Jinja

Config: latest clang self compiled mainline llama.cpp >

import subprocess
import sys

# 1. Set environment variables
env = os.environ.copy()
env["GGML_CUDA_NO_PINNED"] = "1"
env["GGML_CUDA_DISABLE_GRAPHS"] = "1"

# 2. Construct command argument list
cmd = [
    r".\llama-server.exe",
    "-m", r"D:\Laguna-S-2.1-APEX-i-compact.gguf",
    "--reasoning-preserve",
    "--reasoning-budget", "-1",
    "-ngl", "999",
    "--n-cpu-moe", "47",
    "--no-mmap",
    "--mlock",
    "-c", "220000",
    "--cache-type-k", "q8_0",
    "--cache-type-v", "q5_1",
    "-np", "1",
    "-fa", "on",
    "-t", "8",
    "-tb", "8",
    "-b", "2560",
    "-ub", "2560",
    "--jinja",
    "-kvu",
    "--temp", "0.7",
    "--top-p", "0.95",
    "--top-k", "20",
    "--min-p", "0.0",
    "--dry-multiplier", "0.8",
    "--dry-base", "1.75",
    "--dry-allowed-length", "3",
    "--dry-penalty-last-n", "-1",
    "--dry-sequence-breaker", r'\n,:,\",*,;,{,}',
    "--samplers", "top_k;top_p;min_p;temperature;dry",
    "--alias", "laguna-s-2.1",
    "--cache-reuse", "256",
    "--cache-ram", "1024",
    "--ctx-checkpoints", "32",
    "--checkpoint-min-step", "2560",
    "--host", "127.0.0.1",
    "--port", "8080",
    "--verbosity", "4",
    "--chat-template-file", r"G:\xlam3\laguna\chat_template_laguna.jinja",
]

# 3. Execute process
if __name__ == "__main__":
    try:
        print("Starting llama-server...")
        subprocess.run(cmd, env=env, check=True)
    except KeyboardInterrupt:
        print("\nServer stopped by user.")
    except Exception as e:
        print(f"\nError running server: {e}")

Overall - great job! This is probably SOTA for ~64gb shmem local agentic coding as of today

Myric

Owner 5 days ago

Awesome! I'm using Quality on my DGX-spark and it seems to work very well. Glad you found it useful.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment