Instructions to use mlx-community/Laguna-XS-2.1-3bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mlx-community/Laguna-XS-2.1-3bit 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-2.1-3bit")

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-2.1-3bit 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-2.1-3bit"

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-2.1-3bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use mlx-community/Laguna-XS-2.1-3bit 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-2.1-3bit"

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-2.1-3bit

Run Hermes

hermes

OpenClaw new

How to use mlx-community/Laguna-XS-2.1-3bit with OpenClaw:

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-2.1-3bit"

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 "mlx-community/Laguna-XS-2.1-3bit" \
  --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 mlx-community/Laguna-XS-2.1-3bit 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-2.1-3bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "mlx-community/Laguna-XS-2.1-3bit"
# 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-2.1-3bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Laguna-XS-2.1 (MLX, 3bit)

Converted from poolside/Laguna-XS-2.1 to MLX format, quantized to 3 bits (group size 64, 3.503 bpw effective).

Notes

Works with mlx-vlm and oMLX (forcing the model's vlm mode). mlx-lm doesn't support the laguna architecture yet — there's an open PR: mlx-lm#1223.
Sometimes I got an empty </think> tag at the start of responses, which isn't that common. It won't affect anything tho.

Performance

Measured with oMLX's benchmark harness on a Macbook Pro M5 Max 128GB 40 GPU (single request, 128 generated tokens):

prompt	gen tok/s	prefill tok/s	TTFT ms	peak GB
1k	137.2	3959	259	14.3
4k	128.8	4003	1023	14.9
8k	124.4	3807	2152	15.0
16k	114.6	3214	5098	15.3
32k	98.8	2612	12546	15.9

Variants

Variant	bpw	Disk	gen tok/s (1k → 32k)
bf16	16	62 GB	70.6 → 58.7
8bit	8.500	33 GB	95.4 → 76.7
6bit	6.501	25 GB	102.9 → 80.9
5bit	5.502	21 GB	115.9 → 87.7
4bit	4.503	18 GB	126.0 → 91.3
3bit (this repo)	3.503	14 GB	137.2 → 98.8

Usage

uvx --from mlx-vlm mlx_vlm.generate --model mlx-community/Laguna-XS-2.1-3bit --prompt "..." --max-tokens 300

License

OpenMDW-1.1, inherited from the base model.

Downloads last month: 195

Safetensors

Model size

4B params

Tensor type

BF16

U32

MLX

Hardware compatibility

3-bit

Model tree for mlx-community/Laguna-XS-2.1-3bit

Base model

poolside/Laguna-XS-2.1

Quantized

(14)

this model

Collection including mlx-community/Laguna-XS-2.1-3bit

Laguna-XS-2.1

Collection

MLX versions of Laguna-XS-2.1 • 6 items • Updated 8 days ago

Evaluation results

SWE-bench/SWE-bench_Verified · Swe Bench Resolved View evaluation results source leaderboard

70.9
ScaleAI/SWE-bench_Pro · SWE Bench Pro View evaluation results source leaderboard

47.6
harborframework/terminal-bench-2.0 · Terminalbench 2 View evaluation results source leaderboard

37.5