Instructions to use mlx-community/Laguna-XS.2-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mlx-community/Laguna-XS.2-4bit with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Laguna-XS.2-4bit")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use mlx-community/Laguna-XS.2-4bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "mlx-community/Laguna-XS.2-4bit"

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "mlx-community/Laguna-XS.2-4bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use mlx-community/Laguna-XS.2-4bit with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "mlx-community/Laguna-XS.2-4bit"

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 mlx-community/Laguna-XS.2-4bit

Run Hermes

hermes

MLX LM

How to use mlx-community/Laguna-XS.2-4bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "mlx-community/Laguna-XS.2-4bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "mlx-community/Laguna-XS.2-4bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "mlx-community/Laguna-XS.2-4bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Unable to load with mlx-lm 0.31.3 — architecture not recognized

by skaman5 - opened 30 days ago

Discussion

skaman5

30 days ago

Tested loading this model with mlx-lm and it fails due to the laguna architecture not being recognized.

Environment

mlx-lm: 0.31.3
MLX: 0.31.2
Hardware: MacBook Pro M1 Max (24-core GPU), 32 GB unified memory
macOS: 26.4.1

What I tried

mlx_lm.server --model mlx-community/Laguna-XS.2-4bit --port 8080

Fails during model load — the laguna architecture is not in mlx-lm's supported architecture list.

Cross-reference

The GGUF variant (Lucebox/Laguna-XS.2-GGUF) also fails on:

llama.cpp build 9330 (ggml-org/llama.cpp#23249)
LM Studio 0.4.14+4
Ollama 0.24.0

vLLM 0.21.0 has merged support (vllm-project/vllm#41129), confirming the architecture is implementable. vLLM Metal (Apple Silicon plugin, v0.2.0) does not yet include Laguna in its supported models list either.

Model info

Laguna-XS.2 by Poolside AI — 33B total / 3B active MoE, 256 experts + 1 shared, sliding window attention 512 tokens, 131K context, Apache 2.0.

Happy to re-test when mlx-lm adds support for this architecture.

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