Instructions to use Myric/Laguna-S-2.1-APEX-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 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 Desktop

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

Run Pi

# Start Pi in your project directory:
pi

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

Hermes Agent

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

OpenClaw

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"

Novel APEX Quant of Laguna-S-2.1 (agentic coding, DFlash)

by Myric - opened Jul 23

Discussion

Myric

Owner Jul 23

Hugging Face CLI

🧩 New: APEX (MoE-aware mixed-precision) GGUF quants of Laguna-S-2.1 — a 118B-total / ~8B-active agentic-coding MoE, i-quality / i-compact / i-mini tiers, paired with the DFlash speculative-decoding draft for fast local coding.
Built on @poolside's Laguna-S-2.1 + DFlash draft, @unsloth's bf16 GGUF + reused imatrix, and the APEX recipe from @mudler / LocalAI. Thanks all 🙏
https://huggingface.co/Myric/Laguna-S-2.1-APEX-GGUF

scottgl

Jul 23

Which DFlash draft model file should I use?

Myric

Owner Jul 24

Oops, I forgot to upload that one, but give me a few minutes. I discovered with Qwen 3.5 that the drafter works best if you match it to the quant. I'll upload an optimized one with an appropriate encoding. Which size were you interested in using? I can hit that one first.

scottgl

Jul 24

•

edited Jul 24

The quality quant please, thanks. I'm assuming you meant which APEX model I am targeting.

Myric

Owner Jul 24

I didn't actually quantize the drafter yet so I didn't upload it. I verified these quants do work with the stock bf16 encoder (https://huggingface.co/poolside/Laguna-S-2.1-GGUF/tree/main), but I'm about to upload a q8 one which is half the size and another to pair with the smaller quants.

Myric

Owner Jul 24

This new one performs basically identically to the stock drafter and saves a GB: https://huggingface.co/Myric/Laguna-S-2.1-APEX-GGUF/blob/main/laguna-s-2.1-DFlash-Q8_0.gguf

Myric

Owner Jul 24

Honestly, I copied the guidance from Laguna but they're probably running this on big iron where their high speed memory can more than keep up with their compute. On my DGX-Spark, it's snappy enough I mostly didn't bother with the drafter to get an extra few % speed. I'm adding a table to show the differences in speed. The Drafter guesses ahead, kind of like speculative execution on a CPU. It does not affect the output at all, but speeds things up slightly.

I'm throwing a q4 up as well which gave me maybe another 1% and is down to 652MB. I'm also adding a table with a no-drafter run so you can see the difference.

Myric changed discussion status to closed Jul 24

Myric

Owner Jul 24

OK, I stand corrected. The q4 drafter gave me a 20% boost vs the no-drafter run.

Myric

Owner Jul 25

Ok yes @scottgl I added two drafter quants, but the fastest is actually the q4 across the board. I added tables with some measurements.

Myric

Owner Jul 25

https://huggingface.co/Myric/Laguna-S-2.1-APEX-GGUF/blob/main/laguna-s-2.1-DFlash-Q4_K.gguf <-- This one ended up being best in every case I measured.

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