Instructions to use mlx-community/Laguna-S-2.1-oQ3e-fast with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mlx-community/Laguna-S-2.1-oQ3e-fast 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-S-2.1-oQ3e-fast")

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-S-2.1-oQ3e-fast 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-S-2.1-oQ3e-fast"

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-S-2.1-oQ3e-fast"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use mlx-community/Laguna-S-2.1-oQ3e-fast 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-S-2.1-oQ3e-fast"

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-S-2.1-oQ3e-fast

Run Hermes

hermes

OpenClaw new

How to use mlx-community/Laguna-S-2.1-oQ3e-fast 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-S-2.1-oQ3e-fast"

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-S-2.1-oQ3e-fast" \
  --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-S-2.1-oQ3e-fast 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-S-2.1-oQ3e-fast"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "mlx-community/Laguna-S-2.1-oQ3e-fast"
# 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-S-2.1-oQ3e-fast",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

gabfssilva commited on 6 days ago

Commit

c7ba3ed

verified ·

1 Parent(s): e807f41

Single theme-neutral ladder.png (#808080); revert <picture>, drop dark variant

Browse files

Files changed (3) hide show

README.md +1 -4
ladder-dark.png +0 -0
ladder.png +0 -0

README.md CHANGED Viewed

@@ -118,10 +118,7 @@ mmlu_pro, mathqa and winogrande, n=300 seeded samples each, thinking off. This b
 oMLX LM engine directly (greedy, mathqa/winogrande at 1024 max tokens so reasoning isn't truncated).
 Standard error at this n is around 2.5 points, so the oQ3e-fast and the oQ3e are indistinguishable here.
-<picture>
-  <source media="(prefers-color-scheme: dark)" srcset="ladder-dark.png">
-  <img alt="Accuracy vs bits per weight, three benchmarks, n=300" src="ladder.png">
-</picture>
 | Variant | Size | bpw | gen tok/s (1k → 64k) | mmlu_pro | mathqa | winogrande |
 |---|---|---|---|---|---|---|

 oMLX LM engine directly (greedy, mathqa/winogrande at 1024 max tokens so reasoning isn't truncated).
 Standard error at this n is around 2.5 points, so the oQ3e-fast and the oQ3e are indistinguishable here.
+![Accuracy vs bits per weight, three benchmarks, n=300](ladder.png)
 | Variant | Size | bpw | gen tok/s (1k → 64k) | mmlu_pro | mathqa | winogrande |
 |---|---|---|---|---|---|---|

ladder-dark.png DELETED Viewed

Binary file (51.9 kB)

ladder.png CHANGED Viewed