Instructions to use BugTraceAI/BugTraceAI-Apex-G4-26B-Q4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use BugTraceAI/BugTraceAI-Apex-G4-26B-Q4 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="BugTraceAI/BugTraceAI-Apex-G4-26B-Q4",
	filename="BugTraceAI-Apex-G4-26B-Q4.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use BugTraceAI/BugTraceAI-Apex-G4-26B-Q4 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 BugTraceAI/BugTraceAI-Apex-G4-26B-Q4
# Run inference directly in the terminal:
llama cli -hf BugTraceAI/BugTraceAI-Apex-G4-26B-Q4

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf BugTraceAI/BugTraceAI-Apex-G4-26B-Q4
# Run inference directly in the terminal:
llama cli -hf BugTraceAI/BugTraceAI-Apex-G4-26B-Q4

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 BugTraceAI/BugTraceAI-Apex-G4-26B-Q4
# Run inference directly in the terminal:
./llama-cli -hf BugTraceAI/BugTraceAI-Apex-G4-26B-Q4

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 BugTraceAI/BugTraceAI-Apex-G4-26B-Q4
# Run inference directly in the terminal:
./build/bin/llama-cli -hf BugTraceAI/BugTraceAI-Apex-G4-26B-Q4

Use Docker

docker model run hf.co/BugTraceAI/BugTraceAI-Apex-G4-26B-Q4

LM Studio
Jan
Ollama
How to use BugTraceAI/BugTraceAI-Apex-G4-26B-Q4 with Ollama:
```
ollama run hf.co/BugTraceAI/BugTraceAI-Apex-G4-26B-Q4
```

Unsloth Studio

How to use BugTraceAI/BugTraceAI-Apex-G4-26B-Q4 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 BugTraceAI/BugTraceAI-Apex-G4-26B-Q4 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 BugTraceAI/BugTraceAI-Apex-G4-26B-Q4 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for BugTraceAI/BugTraceAI-Apex-G4-26B-Q4 to start chatting

How to use BugTraceAI/BugTraceAI-Apex-G4-26B-Q4 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf BugTraceAI/BugTraceAI-Apex-G4-26B-Q4

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": "BugTraceAI/BugTraceAI-Apex-G4-26B-Q4"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use BugTraceAI/BugTraceAI-Apex-G4-26B-Q4 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf BugTraceAI/BugTraceAI-Apex-G4-26B-Q4

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 BugTraceAI/BugTraceAI-Apex-G4-26B-Q4

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use BugTraceAI/BugTraceAI-Apex-G4-26B-Q4 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf BugTraceAI/BugTraceAI-Apex-G4-26B-Q4

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 "BugTraceAI/BugTraceAI-Apex-G4-26B-Q4" \
  --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 BugTraceAI/BugTraceAI-Apex-G4-26B-Q4 with Docker Model Runner:
```
docker model run hf.co/BugTraceAI/BugTraceAI-Apex-G4-26B-Q4
```

Lemonade

How to use BugTraceAI/BugTraceAI-Apex-G4-26B-Q4 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull BugTraceAI/BugTraceAI-Apex-G4-26B-Q4

Run and chat with the model

lemonade run user.BugTraceAI-Apex-G4-26B-Q4-{{QUANT_TAG}}

List all available models

lemonade list

Dropping Tools

by SemKara - opened Apr 18

Discussion

SemKara

Apr 18

I've had several rounds of using this model where it drops commands to follow up with tool work (edit file, create files, scan file info, directory scan).
I did use the recommended sampling (temp 0.1, top p 0.9, repeat pen 1.1)

PaulthePirate

Apr 20

Same here. Seems good for chat, but it's completely unusable with tools. I also ran it with recommended settings.

Albert-yz9yt

BugTraceAI org May 11

New model for tooling:
https://huggingface.co/BugTraceAI/BugTraceAI-CORE-Ultra-27B-Q4

bullybutcher

29 days ago

I think Apex G4 just needs an updated jinja template. BugTraceAI-CORE-Ultra-27B-Q4 is too much for my hardware.

Albert-yz9yt

BugTraceAI org 28 days ago

I think Apex G4 just needs an updated jinja template. BugTraceAI-CORE-Ultra-27B-Q4 is too much for my hardware.
Hello everyone! Just to clarify the purpose of this model:

Apex G4 is a THINKING model: This model (based on Gemma-4 MOE) is explicitly fine-tuned for deep reasoning and chain-of-thought, not for tool-calling/agentic tasks. Updating the Jinja template will not give it tooling capabilities because it simply wasn't trained for that objective.
Hardware requirements for Ultra: @bullybutcher , the CORE-Ultra-27B-Q4 actually has practically the exact same VRAM footprint as the Apex-G4-26B-Q4. If your hardware can run Apex, you can absolutely run Ultra. You might just need to check your context window settings!
Dedicated Tooling Models: If your workflow requires executing tools, file manipulation, or agentic behaviors, you should use our dedicated CORE series: - BugTraceAI-CORE-Ultra-27B-Q4 - BugTraceAI-CORE-Pro - BugTraceAI-CORE-Fast

@bullybutcher I highly recommend you try our smaller models like CORE-Pro or CORE-Fast. You will be surprised by how a smaller, specifically fine-tuned model for tooling completely outperforms a much larger generalist model in agentic tasks. Give them a try!

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment