Instructions to use altic-dev/fluid-1-mini with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use altic-dev/fluid-1-mini with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf altic-dev/fluid-1-mini:Q6_K
# Run inference directly in the terminal:
llama cli -hf altic-dev/fluid-1-mini:Q6_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf altic-dev/fluid-1-mini:Q6_K
# Run inference directly in the terminal:
llama cli -hf altic-dev/fluid-1-mini:Q6_K

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf altic-dev/fluid-1-mini:Q6_K
# Run inference directly in the terminal:
./llama-cli -hf altic-dev/fluid-1-mini:Q6_K

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf altic-dev/fluid-1-mini:Q6_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf altic-dev/fluid-1-mini:Q6_K

Use Docker

docker model run hf.co/altic-dev/fluid-1-mini:Q6_K

LM Studio
Jan
Ollama
How to use altic-dev/fluid-1-mini with Ollama:
```
ollama run hf.co/altic-dev/fluid-1-mini:Q6_K
```

Unsloth Studio

How to use altic-dev/fluid-1-mini with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for altic-dev/fluid-1-mini to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for altic-dev/fluid-1-mini to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for altic-dev/fluid-1-mini to start chatting

How to use altic-dev/fluid-1-mini with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf altic-dev/fluid-1-mini:Q6_K

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "altic-dev/fluid-1-mini:Q6_K"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use altic-dev/fluid-1-mini with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf altic-dev/fluid-1-mini:Q6_K

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:Q6_K" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

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

Docker Model Runner
How to use altic-dev/fluid-1-mini with Docker Model Runner:
```
docker model run hf.co/altic-dev/fluid-1-mini:Q6_K
```

Lemonade

How to use altic-dev/fluid-1-mini with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull altic-dev/fluid-1-mini:Q6_K

Run and chat with the model

lemonade run user.fluid-1-mini-Q6_K

List all available models

lemonade list

Hermes Agent

How to use altic-dev/fluid-1-mini with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf altic-dev/fluid-1-mini:Q6_K

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:Q6_K

Run Hermes

hermes

Atomic Chat

Fluid-1 Mini

Experimental FluidIntelligence dictation model for local on-device use. This is a preview checkpoint, not a released model.

Model

fluid-1-mini-q6_k.gguf
Base architecture: Qwen3.5 (qwen3_5, text-only export; vision tower excluded)
Parameters: ~2B text
Quantization: Q6_K
SHA-256: 1c83ac7acaed9efbdd278a0cc56f15ffb59f85cf7684da817e8357cdcc915147
Size: 1,606,323,744 bytes
Converted with llama.cpp b9870
Requires a llama.cpp build with qwen35 support (b9870 or newer)

Intended use

Cleaning voice dictation into written text: filler removal, self-correction chains, punctuation, capitalization, paragraph and list formatting, and email shaping. It is not a general assistant and should not be used to answer questions.

The paired system prompt is polish-detailed-compact-v1.md in this repo. The model is tuned against it; substituting a different prompt measurably changes output quality.

License

This model is a Qwen3.5 derivative. The base model's terms apply.

Additional restriction by Altic: this model is licensed only for personal, non-commercial use. You may not use, copy, redistribute, host, bundle, fine-tune, sell, sublicense, or provide access to this model for any commercial, organizational, internal business, research, product, service, or revenue-generating purpose without prior written permission.

Commercial licensing is available by contacting the owner.

Downloads last month: 5

GGUF

Model size

2B params

Architecture

qwen35

Hardware compatibility

6-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support