Instructions to use FlushnetAI/Chronos-DX-Dense-32B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use FlushnetAI/Chronos-DX-Dense-32B-GGUF 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 FlushnetAI/Chronos-DX-Dense-32B-GGUF
# Run inference directly in the terminal:
llama cli -hf FlushnetAI/Chronos-DX-Dense-32B-GGUF

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf FlushnetAI/Chronos-DX-Dense-32B-GGUF
# Run inference directly in the terminal:
llama cli -hf FlushnetAI/Chronos-DX-Dense-32B-GGUF

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 FlushnetAI/Chronos-DX-Dense-32B-GGUF
# Run inference directly in the terminal:
./llama-cli -hf FlushnetAI/Chronos-DX-Dense-32B-GGUF

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 FlushnetAI/Chronos-DX-Dense-32B-GGUF
# Run inference directly in the terminal:
./build/bin/llama-cli -hf FlushnetAI/Chronos-DX-Dense-32B-GGUF

Use Docker

docker model run hf.co/FlushnetAI/Chronos-DX-Dense-32B-GGUF

LM Studio
Jan

vLLM

How to use FlushnetAI/Chronos-DX-Dense-32B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FlushnetAI/Chronos-DX-Dense-32B-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FlushnetAI/Chronos-DX-Dense-32B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/FlushnetAI/Chronos-DX-Dense-32B-GGUF

Ollama
How to use FlushnetAI/Chronos-DX-Dense-32B-GGUF with Ollama:
```
ollama run hf.co/FlushnetAI/Chronos-DX-Dense-32B-GGUF
```
Unsloth Desktop

How to use FlushnetAI/Chronos-DX-Dense-32B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf FlushnetAI/Chronos-DX-Dense-32B-GGUF

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "FlushnetAI/Chronos-DX-Dense-32B-GGUF"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use FlushnetAI/Chronos-DX-Dense-32B-GGUF with Docker Model Runner:
```
docker model run hf.co/FlushnetAI/Chronos-DX-Dense-32B-GGUF
```

Lemonade

How to use FlushnetAI/Chronos-DX-Dense-32B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull FlushnetAI/Chronos-DX-Dense-32B-GGUF

Run and chat with the model

lemonade run user.Chronos-DX-Dense-32B-GGUF-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use FlushnetAI/Chronos-DX-Dense-32B-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf FlushnetAI/Chronos-DX-Dense-32B-GGUF

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 FlushnetAI/Chronos-DX-Dense-32B-GGUF

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use FlushnetAI/Chronos-DX-Dense-32B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf FlushnetAI/Chronos-DX-Dense-32B-GGUF

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 "FlushnetAI/Chronos-DX-Dense-32B-GGUF" \
  --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"

Chronos-DX Dense 32B

By Flushnet AI

A dense language model for local text generation and AI applications.

Model type	Total parameters	Active parameters	Format
Dense	32.085B	~32B	GGUF · Q3_K

Chronos-DX architecture and GGUF compatibility

Chronos-DX has its own proprietary architecture, with internal architectural details not publicly disclosed by Flushnet AI.

Because the native Chronos-DX architecture type is not currently defined in standard llama.cpp, the Chronos-DX Dense 32B GGUF was adapted to the supported qwen2 architecture type and compatible tensor format so it can run with standard llama.cpp and compatible Ollama installations.

The qwen2 label displayed automatically by Hugging Face is therefore the compatibility type of this GGUF export, not the name or a full technical description of the proprietary Chronos-DX architecture.

Chronos-DX demos: two flavours

Chronos-DX demos are available in two flavours:

Local Private Secure Browser Demo — a compressed, browser-based version designed for local and private use.
Dense 32B GGUF — the full dense model distributed as a downloadable GGUF for local inference, with 32.085B total parameters (~32B active).

Explore Chronos-DX on Flushnet and the Chronos-DX Ollama listing. The Ollama listing is a project page; local model weights are currently provided by the GGUF repository above.

Knowledge areas

Technology: software engineering, systems architecture, cloud infrastructure, AI and data science
Quantitative fields: mathematics, logic, science and technical subjects
Business: strategy, management, operations, economics and finance
Language: writing, communication, multilingual content and translation
Research & culture: education, history and humanities

Training & customization

Need Chronos-DX tailored to your field, data or infrastructure?

Request training, customization, RAG integration, performance optimization or model repair →

Download and run with Ollama

Ollama downloads the GGUF directly from this public Hugging Face repository:

ollama pull hf.co/FlushnetAI/Chronos-DX-Dense-32B-GGUF:Chronos-DX-Dense-32B-Q3_K.gguf
ollama run hf.co/FlushnetAI/Chronos-DX-Dense-32B-GGUF:Chronos-DX-Dense-32B-Q3_K.gguf

Repeat the pull command when you want an updated public model revision; installed local copies do not update automatically.

Other local runtimes

The recommended formats for this release are Ollama or llama.cpp with the published GGUF file. The example filename below is `Chronos-DX-Dense-32B-Q3_K.gguf`.

llama.cpp CLI and local API

Install a recent llama.cpp release and use its `llama-cli` or `llama-server` executables.

# Download once from Hugging Face
hf download FlushnetAI/Chronos-DX-Dense-32B-GGUF Chronos-DX-Dense-32B-Q3_K.gguf --local-dir .

# Interactive local inference
llama-cli -m ./Chronos-DX-Dense-32B-Q3_K.gguf -cnv

# Local HTTP API + browser chat interface
llama-server -m ./Chronos-DX-Dense-32B-Q3_K.gguf --host 127.0.0.1 --port 8080

The local server's OpenAI-compatible chat endpoint is `http://127.0.0.1:8080/v1/chat/completions\`.

vLLM (advanced / conditional)

vLLM uses an optional GGUF plugin. This particular 32B release has not been verified with vLLM, and loading requires a compatible Hugging Face tokenizer and model configuration. For capable GPU systems, once those compatible assets are available:

pip install vllm vllm-gguf-plugin

# After downloading the GGUF as shown above:
vllm serve ./Chronos-DX-Dense-32B-Q3_K.gguf \
  --tokenizer /path/to/matching-tokenizer \
  --hf-config-path /path/to/matching-model-config

These are prerequisites, not a claim of out-of-the-box support. Refer to the vLLM GGUF guide.

Hugging Face Transformers (advanced / conditional)

Transformers supports GGUF loading through `gguf_file`. It may require matching tokenizer/config assets, a supported loader and substantially more memory because quantized weights can be dequantized. Direct loading of this 32B artifact has not been verified with Transformers.

from transformers import AutoModelForCausalLM, AutoTokenizer

repo = "FlushnetAI/Chronos-DX-Dense-32B-GGUF"
gguf = "Chronos-DX-Dense-32B-Q3_K.gguf"

# Use only once compatible config/tokenizer support is available.
tokenizer = AutoTokenizer.from_pretrained(repo, gguf_file=gguf)
model = AutoModelForCausalLM.from_pretrained(repo, gguf_file=gguf)

For memory-efficient local use of the published Q3_K artifact, prefer Ollama or llama.cpp. See Transformers GGUF documentation.

Desktop apps

GGUF-compatible desktop runtimes such as LM Studio may be used to import the downloaded file. Compatibility depends on the version and hardware.

Download & updates

Download Chronos-DX-Dense-32B-Q3_K.gguf from Files and versions.

This repository hosts the current public GGUF. Previously downloaded local copies must be refreshed to receive updates.

Downloads last month: -

GGUF

Model size

32B params

Architecture

qwen2

Hardware compatibility