Instructions to use nace-ai/drex-v2.0-Q8_0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use nace-ai/drex-v2.0-Q8_0 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 nace-ai/drex-v2.0-Q8_0:Q8_0
# Run inference directly in the terminal:
llama cli -hf nace-ai/drex-v2.0-Q8_0:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf nace-ai/drex-v2.0-Q8_0:Q8_0
# Run inference directly in the terminal:
llama cli -hf nace-ai/drex-v2.0-Q8_0:Q8_0

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 nace-ai/drex-v2.0-Q8_0:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf nace-ai/drex-v2.0-Q8_0:Q8_0

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 nace-ai/drex-v2.0-Q8_0:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf nace-ai/drex-v2.0-Q8_0:Q8_0

Use Docker

docker model run hf.co/nace-ai/drex-v2.0-Q8_0:Q8_0

Llama new
LM Studio
Jan
Ollama
How to use nace-ai/drex-v2.0-Q8_0 with Ollama:
```
ollama run hf.co/nace-ai/drex-v2.0-Q8_0:Q8_0
```
Unsloth Desktop

How to use nace-ai/drex-v2.0-Q8_0 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf nace-ai/drex-v2.0-Q8_0:Q8_0

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": "nace-ai/drex-v2.0-Q8_0:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use nace-ai/drex-v2.0-Q8_0 with Docker Model Runner:
```
docker model run hf.co/nace-ai/drex-v2.0-Q8_0:Q8_0
```

Lemonade

How to use nace-ai/drex-v2.0-Q8_0 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull nace-ai/drex-v2.0-Q8_0:Q8_0

Run and chat with the model

lemonade run user.drex-v2.0-Q8_0-Q8_0

List all available models

lemonade list

Hermes Agent

How to use nace-ai/drex-v2.0-Q8_0 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf nace-ai/drex-v2.0-Q8_0:Q8_0

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 nace-ai/drex-v2.0-Q8_0:Q8_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use nace-ai/drex-v2.0-Q8_0 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf nace-ai/drex-v2.0-Q8_0:Q8_0

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 "nace-ai/drex-v2.0-Q8_0:Q8_0" \
  --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"

Drex v2.0 Q8_0 GGUF

A Q8_0 GGUF of Drex v2.0, a decision model that takes a state and named typed questions and returns a probability for every option. The file is 36.9 GB, about half the size of the bf16 weights.

Drex v2.0 · Drex repository · llama.cpp fork (branch drex-v2.0) · Ollama fork (branch drex-v2.0)

Run with llama.cpp

Build the drex-v2.0 branch of the llama.cpp fork as described on the model page. Then download the GGUF and start the server:

hf download nace-ai/drex-v2.0-Q8_0 drex-v2.0-Q8_0.gguf --local-dir weights/drex-v2.0-Q8_0

llama.cpp/build/bin/llama-server -m weights/drex-v2.0-Q8_0/drex-v2.0-Q8_0.gguf \
  --embedding --pooling none -np 2 -c 32768 -b 16384 -ub 2048 -ngl 28 --port 8000

The server answers POST /v1/systemone; the request format is in the repository docs. On a 48 GB Mac, -ngl 28 offloads 28 layers to Metal and runs the rest on the CPU; -ngl 0 runs entirely on the CPU. This command accepts requests up to 16,384 tokens; for larger windows see Context length.

Run with Ollama

Use the Nace fork of Ollama from the model page, with this Modelfile next to the GGUF:

FROM ./drex-v2.0-Q8_0.gguf
CAPABILITY decision
PARAMETER num_ctx 16384
PARAMETER num_gpu 28

File

File	Size	SHA-256
`drex-v2.0-Q8_0.gguf`	36,907,336,224 bytes	`dc1ab68ed92b66f445b9e084e92b438330d15378cd6f2726a71f0d9529518cfe`

The GGUF has the qwen35moe architecture. It holds 432 Q8_0 tensors and 306 F32 tensors, converted with --no-mtp.

Tested

On an Apple M5 Pro (48 GB unified memory), the Q8_0 GGUF gives the same answers on Metal with -ngl 28 and on the CPU, with probabilities within 0.03 of each other. Ollama gives the same answers as llama-server.

License

Nace.AI Open RAIL-M license, see LICENSE.

Downloads last month: 2,894

GGUF

Model size

35B params

Architecture

qwen35moe

Hardware compatibility

8-bit

Inference Providers NEW

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

Model tree for nace-ai/drex-v2.0-Q8_0

Base model

Qwen/Qwen3.6-35B-A3B

Finetuned

nace-ai/drex-v2.0

Quantized

(3)

this model