Instructions to use altic-dev/Fluid-1-Mini-2B-MLX-6bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use altic-dev/Fluid-1-Mini-2B-MLX-6bit 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("altic-dev/Fluid-1-Mini-2B-MLX-6bit")

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 altic-dev/Fluid-1-Mini-2B-MLX-6bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "altic-dev/Fluid-1-Mini-2B-MLX-6bit"

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": "altic-dev/Fluid-1-Mini-2B-MLX-6bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use altic-dev/Fluid-1-Mini-2B-MLX-6bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "altic-dev/Fluid-1-Mini-2B-MLX-6bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "altic-dev/Fluid-1-Mini-2B-MLX-6bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "altic-dev/Fluid-1-Mini-2B-MLX-6bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use altic-dev/Fluid-1-Mini-2B-MLX-6bit 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 "altic-dev/Fluid-1-Mini-2B-MLX-6bit"

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 altic-dev/Fluid-1-Mini-2B-MLX-6bit

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use altic-dev/Fluid-1-Mini-2B-MLX-6bit with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "altic-dev/Fluid-1-Mini-2B-MLX-6bit"

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 "altic-dev/Fluid-1-Mini-2B-MLX-6bit" \
  --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"

Fluid-1-Mini-2B-MLX-6bit / ALTIC-MODEL-TERMS.md

ALTICDEV

Add files using upload-large-folder tool

8153547 verified about 10 hours ago

preview code

Raw

History Blame Contribute Delete

1.27 kB

ALTIC FluidVoice Apps-Only Model Terms

These terms apply to ALTIC's fine-tuning, parameter modifications, optimization, conversion, and packaging of Fluid-1 Mini (the "ALTIC Contributions").

Permission

ALTIC grants a limited, non-exclusive, non-transferable permission to use the ALTIC Contributions only through official FluidVoice applications developed and distributed by ALTIC.

Prohibited uses

Any use outside official FluidVoice applications is prohibited. Without ALTIC's prior written permission, you may not copy, use, redistribute, mirror, host, bundle, modify, fine-tune, sell, sublicense, extract, reverse engineer, or integrate the ALTIC Contributions into any third-party application, product, service, SDK, model, or hosted API.

Upstream components

This distribution is derived from Qwen3.5-2B. Qwen-derived components remain subject to Apache License 2.0. Nothing in these terms restricts rights granted directly by upstream copyright holders. The Apache License 2.0 text is included in LICENSE-QWEN-APACHE-2.0.

Disclaimer

THE ALTIC CONTRIBUTIONS ARE PROVIDED "AS IS", WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, TO THE MAXIMUM EXTENT PERMITTED BY LAW.