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

Libraries

How to use AtomicChat/Laguna-XS-2.1-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="AtomicChat/Laguna-XS-2.1-GGUF",
	filename="Laguna-XS-2.1-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 AtomicChat/Laguna-XS-2.1-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 AtomicChat/Laguna-XS-2.1-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf AtomicChat/Laguna-XS-2.1-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf AtomicChat/Laguna-XS-2.1-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf AtomicChat/Laguna-XS-2.1-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 AtomicChat/Laguna-XS-2.1-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf AtomicChat/Laguna-XS-2.1-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 AtomicChat/Laguna-XS-2.1-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf AtomicChat/Laguna-XS-2.1-GGUF:Q4_K_M

Use Docker

docker model run hf.co/AtomicChat/Laguna-XS-2.1-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use AtomicChat/Laguna-XS-2.1-GGUF with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/AtomicChat/Laguna-XS-2.1-GGUF:Q4_K_M

Ollama
How to use AtomicChat/Laguna-XS-2.1-GGUF with Ollama:
```
ollama run hf.co/AtomicChat/Laguna-XS-2.1-GGUF:Q4_K_M
```

Unsloth Studio

How to use AtomicChat/Laguna-XS-2.1-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 AtomicChat/Laguna-XS-2.1-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 AtomicChat/Laguna-XS-2.1-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

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

How to use AtomicChat/Laguna-XS-2.1-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf AtomicChat/Laguna-XS-2.1-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": "AtomicChat/Laguna-XS-2.1-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use AtomicChat/Laguna-XS-2.1-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 AtomicChat/Laguna-XS-2.1-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 AtomicChat/Laguna-XS-2.1-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use AtomicChat/Laguna-XS-2.1-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf AtomicChat/Laguna-XS-2.1-GGUF:Q4_K_M

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 "AtomicChat/Laguna-XS-2.1-GGUF:Q4_K_M" \
  --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 AtomicChat/Laguna-XS-2.1-GGUF with Docker Model Runner:
```
docker model run hf.co/AtomicChat/Laguna-XS-2.1-GGUF:Q4_K_M
```

Lemonade

How to use AtomicChat/Laguna-XS-2.1-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull AtomicChat/Laguna-XS-2.1-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Laguna-XS-2.1-GGUF-Q4_K_M

List all available models

lemonade list

Base model: poolside/Laguna-XS-2.1

Laguna XS 2.1, quantized to GGUF by Atomic Chat with an importance matrix. Built straight from poolside's original weights. Runs fully offline on your machine.

Highlights

33B total / 3B active Mixture-of-Experts for agentic coding and long-horizon work on a local machine.
Mixed attention layout: 40 layers, 10 global + 30 sliding-window (3:1 ratio), sigmoid gating with per-layer rotary scales.
256 experts + 1 shared expert, sliding window of 512 tokens.
262,144-token context.
Native interleaved reasoning, enable or disable per request.
Upgraded from Laguna XS.2: +5.4% on SWE-bench Multilingual and stronger terminal-style performance.

Laguna is a new architecture. It runs in Atomic Chat 1.1.135+ out of the box, or in a build of llama.cpp with Laguna support (PR #25165). Stock llama.cpp releases do not load it yet. Always pass --jinja so the chat template is applied.

Model Overview

Property	Value
Base model	`poolside/Laguna-XS-2.1`
Total parameters	33B (3B active per token)
Architecture	Laguna MoE, mixed sliding-window/global attention
Experts	256 + 1 shared
Layers	40 (10 global, 30 sliding-window)
Sliding window	512 tokens
Context length	262,144
Optimizer	Muon
This repo	imatrix GGUF quants for llama.cpp, built from the original weights.

Scores are poolside's published results for the full-precision base poolside/Laguna-XS-2.1. The GGUF quants run the same model locally; lower bit-widths trade a little accuracy for size and speed.

Choosing a quant

All rungs are quantized with an importance matrix (imatrix) calibrated on a general-purpose dataset.

Quant	Size	Notes
`Q3_K_M`	15 GB	smallest, usable
`Q4_K_M`	19 GB	fast, low memory
`Q5_K_M`	23 GB	balanced
`Q6_K`	26 GB	recommended sweet spot
`Q8_0`	34 GB	closest to the original

Q6_K is the best quality/size balance for most setups. Use Q3_K_M/Q4_K_M on tighter memory; Q8_0 when you want maximum fidelity.

Get started

Atomic Chat: open the app (1.1.135+), search AtomicChat/Laguna-XS-2.1-GGUF, pick a quant, hit Use this model.

llama.cpp (build with Laguna support):

llama-cli -m Laguna-XS-2.1-Q6_K.gguf --jinja \
    -p "Write a Python retry wrapper with exponential backoff." -n 512

llama.cpp server:

llama-server -m Laguna-XS-2.1-Q6_K.gguf --jinja -c 8192
# OpenAI-compatible endpoint at http://localhost:8080/v1/chat/completions

Reasoning is native and on by default. For agentic coding, keep reasoning enabled and preserve prior thinking blocks across turns.

Best practices

Parameter	Value
temperature	1.0
top_k	20
top_p	1.0

poolside's benchmark settings.

How these were made

Download poolside's official Laguna-XS-2.1-BF16.gguf.
Build an importance matrix with llama-imatrix on a general calibration set.
Quantize each rung with llama-quantize --imatrix from the BF16 GGUF.

License

Released by poolside under the OpenMDW-1.1 license, which permits free use, modification and redistribution with attribution. GGUF conversion by Atomic Chat. This is an unofficial community quantization and is not endorsed by poolside; the original LICENSE.md and notices of origin are retained in this repo.

Downloads last month: 8,331

GGUF

Model size

33B params

Architecture

laguna

Hardware compatibility

3-bit

4-bit

5-bit

6-bit

8-bit

Model tree for AtomicChat/Laguna-XS-2.1-GGUF

Base model

poolside/Laguna-XS-2.1

Quantized

(16)

this model

Collection including AtomicChat/Laguna-XS-2.1-GGUF

Laguna XS 2.1

Collection

poolside Laguna XS 2.1 (33B/3B MoE) quantized by Atomic Chat - GGUF (llama.cpp) and MLX (Apple Silicon) ladders. • 4 items • Updated 13 days ago • 2