Instructions to use AtomicChat/Laguna-S-2.1-MLX-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AtomicChat/Laguna-S-2.1-MLX-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("AtomicChat/Laguna-S-2.1-MLX-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 AtomicChat/Laguna-S-2.1-MLX-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 "AtomicChat/Laguna-S-2.1-MLX-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": "AtomicChat/Laguna-S-2.1-MLX-4bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use AtomicChat/Laguna-S-2.1-MLX-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 "AtomicChat/Laguna-S-2.1-MLX-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 AtomicChat/Laguna-S-2.1-MLX-4bit

Run Hermes

hermes

OpenClaw new

How to use AtomicChat/Laguna-S-2.1-MLX-4bit with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "AtomicChat/Laguna-S-2.1-MLX-4bit"

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-S-2.1-MLX-4bit" \
  --custom-provider-id mlx-lm \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

MLX LM

How to use AtomicChat/Laguna-S-2.1-MLX-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 "AtomicChat/Laguna-S-2.1-MLX-4bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "AtomicChat/Laguna-S-2.1-MLX-4bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "AtomicChat/Laguna-S-2.1-MLX-4bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Base model: poolside/Laguna-S-2.1

Laguna S 2.1, self-quantized to MLX by Atomic Chat. Built straight from Poolside's original weights with a per-tensor importance matrix, so this is not a repack of somebody else's files. Runs fully offline.

Highlights

117.6B parameters: the weights this repo quantizes.
Context length: 1,048,576 tokens (1M), as published by Poolside.
48 layers: Mixture-of-Experts, hybrid sliding-window (512) and global attention.
Full imatrix ladder: every quant is calibrated with an importance matrix.
Mixed SWA and global attention layout: 48 layers in a 1:3 global-to-SWA ratio (12 global attention layers, 36 sliding-window layers, window 512), with softplus attention gating and per-layer-type rotary scales.
Native reasoning support: interleaved thinking between tool calls, with per-request control via enable_thinking.
Speculative decoding: a trained DFlash draft model is available for lower-latency serving.

These MLXs are self-quantized from the original weights, not a repack. The importance matrix keeps low-bit quants closer to the full-precision model.

Model Overview

Property	Value
Base model	`poolside/Laguna-S-2.1`
Parameters	117.6B
Layers	48
Experts	256 routed (top-10)
Sliding window	512 tokens
Context length	1,048,576 tokens (1M)
Vocabulary	100,352
Modalities	Text
Architecture	Mixture-of-Experts, 256 experts (top-10), hybrid sliding-window (512) and global attention, 48 attention heads over 8 KV heads, `LagunaForCausalLM`
This repo	MLX weights

Benchmarks

Benchmark	Score
Laguna S 2.1	70.2%
Tencent Hy3	71.7%
Inkling	63.8%
Nemotron 3 Ultra	56.4%
DeepSeek-V4-Pro Max	64.0%
Kimi K3	88.3%
Qwen 3.7 Max	74.5%
Muse Spark 1.1	80%
Claude Fable 5	88%

Scores are Poolside's published results for the base poolside/Laguna-S-2.1, not our own measurements. Quantization preserves the large majority of this; Q4_K_M and up stay close to full precision.

Get started

Atomic Chat: search AtomicChat/Laguna-S-2.1-MLX-4bit and hit Use this model.
mlx-lm: mlx_lm.generate --model AtomicChat/Laguna-S-2.1-MLX-4bit --prompt "Hello" --max-tokens 512
Server: mlx_lm.server --model AtomicChat/Laguna-S-2.1-MLX-4bit --port 8080

Best practices

Parameter	Value
temperature	1.0
top_p	1.0
top_k	20
min_p	0.0

Poolside's recommended sampling configuration for poolside/Laguna-S-2.1.

How these were made

Download poolside/Laguna-S-2.1 (original weights).
Convert and quantize with mlx_lm.convert on our pipeline.

License

Original model by Poolside, released under the OpenMDW-1.1 license. Full terms: OpenMDW-1.1. Quantized by Atomic Chat.

Downloads last month: 387

Safetensors

Model size

18B params

Tensor type

BF16

U32

MLX

Hardware compatibility

4-bit

Model tree for AtomicChat/Laguna-S-2.1-MLX-4bit

Base model

poolside/Laguna-S-2.1

Quantized

(65)

this model

Collection including AtomicChat/Laguna-S-2.1-MLX-4bit

Laguna S 2.1

Collection

4 items • Updated 3 days ago

Evaluation results

datacurve/deep-swe · Deep Swe View evaluation results source leaderboard

40.4
ScaleAI/SWE-bench_Pro · SWE Bench Pro View evaluation results source leaderboard

59.4
SWE-bench/SWE-bench_Multilingual · Swe Bench Resolved View evaluation results source

78.5