Instructions to use meshllm/laguna-s-2.1-Q4_K_M-layers with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use meshllm/laguna-s-2.1-Q4_K_M-layers with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="meshllm/laguna-s-2.1-Q4_K_M-layers",
	filename="layers/layer-000.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 meshllm/laguna-s-2.1-Q4_K_M-layers 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 meshllm/laguna-s-2.1-Q4_K_M-layers
# Run inference directly in the terminal:
llama cli -hf meshllm/laguna-s-2.1-Q4_K_M-layers

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf meshllm/laguna-s-2.1-Q4_K_M-layers
# Run inference directly in the terminal:
llama cli -hf meshllm/laguna-s-2.1-Q4_K_M-layers

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 meshllm/laguna-s-2.1-Q4_K_M-layers
# Run inference directly in the terminal:
./llama-cli -hf meshllm/laguna-s-2.1-Q4_K_M-layers

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 meshllm/laguna-s-2.1-Q4_K_M-layers
# Run inference directly in the terminal:
./build/bin/llama-cli -hf meshllm/laguna-s-2.1-Q4_K_M-layers

Use Docker

docker model run hf.co/meshllm/laguna-s-2.1-Q4_K_M-layers

LM Studio
Jan

vLLM

How to use meshllm/laguna-s-2.1-Q4_K_M-layers with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "meshllm/laguna-s-2.1-Q4_K_M-layers"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "meshllm/laguna-s-2.1-Q4_K_M-layers",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/meshllm/laguna-s-2.1-Q4_K_M-layers

Ollama
How to use meshllm/laguna-s-2.1-Q4_K_M-layers with Ollama:
```
ollama run hf.co/meshllm/laguna-s-2.1-Q4_K_M-layers
```

Unsloth Studio

How to use meshllm/laguna-s-2.1-Q4_K_M-layers 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 meshllm/laguna-s-2.1-Q4_K_M-layers 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 meshllm/laguna-s-2.1-Q4_K_M-layers to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for meshllm/laguna-s-2.1-Q4_K_M-layers to start chatting

How to use meshllm/laguna-s-2.1-Q4_K_M-layers with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf meshllm/laguna-s-2.1-Q4_K_M-layers

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": "meshllm/laguna-s-2.1-Q4_K_M-layers"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use meshllm/laguna-s-2.1-Q4_K_M-layers with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf meshllm/laguna-s-2.1-Q4_K_M-layers

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 meshllm/laguna-s-2.1-Q4_K_M-layers

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use meshllm/laguna-s-2.1-Q4_K_M-layers with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf meshllm/laguna-s-2.1-Q4_K_M-layers

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 "meshllm/laguna-s-2.1-Q4_K_M-layers" \
  --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 meshllm/laguna-s-2.1-Q4_K_M-layers with Docker Model Runner:
```
docker model run hf.co/meshllm/laguna-s-2.1-Q4_K_M-layers
```

Lemonade

How to use meshllm/laguna-s-2.1-Q4_K_M-layers with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull meshllm/laguna-s-2.1-Q4_K_M-layers

Run and chat with the model

lemonade run user.laguna-s-2.1-Q4_K_M-layers-{{QUANT_TAG}}

List all available models

lemonade list

laguna-s-2.1-Q4_K_M

Distributed GGUF inference package for Mesh LLM

GGUF layer package for running laguna-s-2.1-Q4_K_M across a local Mesh LLM cluster.

This package is derived from poolside/Laguna-S-2.1-GGUF and keeps the original GGUF distribution split into per-layer artifacts for distributed inference.

Highlights

Run locally	Pool multiple machines	OpenAI-compatible	Package variant
Private inference on your hardware	Split layers across peers	Serve `/v1/chat/completions` locally	`Q4_K_M` layer package

Model Overview

Property	Value
Source model	poolside/Laguna-S-2.1-GGUF
Model id	`poolside/Laguna-S-2.1-GGUF:Q4_K_M`
Family	laguna
Parameter scale	not recorded
Quantization	`Q4_K_M`
Layer count	48
Activation width	3072
Package size	63.7 GB
Source file	`laguna-s-2.1-Q4_K_M.gguf`
Package repo	meshllm/laguna-s-2.1-Q4_K_M-layers

Recommended Use

Local and private inference with Mesh LLM.
Multi-machine serving when the full GGUF is too large for one host.
OpenAI-compatible chat/completions workflows through Mesh LLM's local API.

For upstream architecture details, chat template guidance, sampling recommendations, license terms, and benchmark notes, see the source model card: poolside/Laguna-S-2.1-GGUF.

Default Serving Policy

This pinned Q4_K_M package selects request-local suffix N-gram speculation by default:

suffix match length: 5 to 32 tokens
maximum proposal: 48 tokens
verification window: 1 to 32 tokens
verification pipeline depth: 2

No speculative CLI flags are required on a Mesh LLM build that supports the package window_policy.pipeline_depth field. Older builds ignore that optional field and retain their legacy verification depth of 1.

The default is based on an ordinary two-node Mesh run using an Apple M5 Max / Metal coordinator and an Australian Vast RTX 6000 Ada / CUDA worker. Normal placement selected layers 0..36 / 36..48, with F16 activation wire and a direct Iroh/QUIC path. A 44,460-token repeat/copy prompt plus 65 generated tokens produced identical content across three requests. Suffix N-gram accepted 32 of 64 proposed tokens in each request, reached pipeline depth 2 with two verification windows in flight, and decoded at 19.74, 18.24, and 15.42 tok/s. The 63-request stability harness completed without an HTTP failure; the full retained capture contains 65/65 HTTP 200 responses.

This evidence does not certify structured tool calls, full 256K context saturation, Q8 activation wire, Q8 KV quality, DFlash, or any other Poolside model or quantization. The suffix predictor is workload-dependent: a low-overlap control produced no proposal.

Quickstart

# Run this on each machine that should contribute memory/compute.
mesh-llm serve --model "meshllm/laguna-s-2.1-Q4_K_M-layers" --split

# Check the mesh and discover the OpenAI-compatible model name.
curl -s http://localhost:3131/api/status
curl -s http://localhost:3131/v1/models

# Send an OpenAI-compatible chat request.
curl -s http://localhost:3131/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "poolside/Laguna-S-2.1-GGUF:Q4_K_M",
    "messages": [{"role": "user", "content": "Write a tiny hello-world function in Rust."}],
    "max_tokens": 128
  }'

Package Variant

Property	Value
Format	`layer-package`
Canonical source ref	`poolside/Laguna-S-2.1-GGUF@edd093522473dc7313b0738d8b4116b7f8b9745f/laguna-s-2.1-Q4_K_M.gguf`
Source revision	`edd093522473dc7313b0738d8b4116b7f8b9745f`
Source SHA-256	`a34c74e46688122bef83122f4133031bababbefcf57436dde97048c91e2cc6ff`
Skippy ABI	`0.1.32`
Package manifest SHA-256	`0250cfb54ceeb94a9c71e48df447f780e32fc625553844d6403770f315be0237`

What Is Included

Artifact	Path	Contents	SHA-256
Manifest	`model-package.json`	Package schema, source identity, checksums	`0250cfb54ceeb94a9c71e48df447f780e32fc625553844d6403770f315be0237`
Metadata	`shared/metadata.gguf`	0 tensors, 3.5 MB	`86666ec7909e8d9493fe74b5c5fb7805e597fe52652a454efb9655b0d1beb59b`
Embeddings	`shared/embeddings.gguf`	1 tensors, 315.9 MB	`37e3319cf94f64c3277118a784a7392fc26ca799c0d85fc6f27ea73d11092955`
Output head	`shared/output.gguf`	2 tensors, 315.9 MB	`3c4741b0e93856d699afafa25f9a6e4e9f7deaa23f276fe588a13f174472ea8b`
Transformer layers	`layers/layer-*.gguf`	48 layer artifacts, 811 tensors, 63.1 GB	`see model-package.json`

Validation

Generated by the Mesh LLM HF Jobs splitter from mesh-llm ref feat/laguna-certification. Each artifact is checksummed as it is written, uploaded to this repository, and removed from the job workspace before the next artifact is produced.

skippy-model-package write-package "/source/laguna-s-2.1-Q4_K_M.gguf" --out-dir "/tmp/meshllm-layer-job-meshllm_laguna-s-2.1-Q4_K_M-layers-199/package"

Model tree for meshllm/laguna-s-2.1-Q4_K_M-layers

Base model

poolside/Laguna-S-2.1

Quantized

poolside/Laguna-S-2.1-GGUF

Quantized

(2)

this model

meshllm
/

laguna-s-2.1-Q4_K_M-layers

laguna-s-2.1-Q4_K_M

Highlights

Model Overview

Recommended Use

Default Serving Policy

Quickstart

Package Variant

What Is Included

Validation

Links

Model tree for meshllm/laguna-s-2.1-Q4_K_M-layers