Instructions to use Gogeta70/Qwen_3.6_27B_Opus with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Gogeta70/Qwen_3.6_27B_Opus 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 Gogeta70/Qwen_3.6_27B_Opus:BF16
# Run inference directly in the terminal:
llama cli -hf Gogeta70/Qwen_3.6_27B_Opus:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Gogeta70/Qwen_3.6_27B_Opus:BF16
# Run inference directly in the terminal:
llama cli -hf Gogeta70/Qwen_3.6_27B_Opus:BF16

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 Gogeta70/Qwen_3.6_27B_Opus:BF16
# Run inference directly in the terminal:
./llama-cli -hf Gogeta70/Qwen_3.6_27B_Opus:BF16

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 Gogeta70/Qwen_3.6_27B_Opus:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Gogeta70/Qwen_3.6_27B_Opus:BF16

Use Docker

docker model run hf.co/Gogeta70/Qwen_3.6_27B_Opus:BF16

LM Studio
Jan
Ollama
How to use Gogeta70/Qwen_3.6_27B_Opus with Ollama:
```
ollama run hf.co/Gogeta70/Qwen_3.6_27B_Opus:BF16
```

Unsloth Studio

How to use Gogeta70/Qwen_3.6_27B_Opus 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 Gogeta70/Qwen_3.6_27B_Opus 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 Gogeta70/Qwen_3.6_27B_Opus to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Gogeta70/Qwen_3.6_27B_Opus to start chatting

How to use Gogeta70/Qwen_3.6_27B_Opus with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Gogeta70/Qwen_3.6_27B_Opus:BF16

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": "Gogeta70/Qwen_3.6_27B_Opus:BF16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Gogeta70/Qwen_3.6_27B_Opus with Docker Model Runner:
```
docker model run hf.co/Gogeta70/Qwen_3.6_27B_Opus:BF16
```

Lemonade

How to use Gogeta70/Qwen_3.6_27B_Opus with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Gogeta70/Qwen_3.6_27B_Opus:BF16

Run and chat with the model

lemonade run user.Qwen_3.6_27B_Opus-BF16

List all available models

lemonade list

Hermes Agent

How to use Gogeta70/Qwen_3.6_27B_Opus with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Gogeta70/Qwen_3.6_27B_Opus:BF16

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 Gogeta70/Qwen_3.6_27B_Opus:BF16

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Gogeta70/Qwen_3.6_27B_Opus with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Gogeta70/Qwen_3.6_27B_Opus:BF16

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 "Gogeta70/Qwen_3.6_27B_Opus:BF16" \
  --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"

This is a finetune of the Qwen 3.6 27B base model on the angrygiraffe/claude-opus-4.6-4.7-reasoning-8.7k dataset using unsloth studio.

I haven't run any benchmarks, but a cursory test of the model seems to demonstrate a significant improvement in the model's output. Specifically, it appears to need much less reasoning before coming to a conclusion and providing a response.

I have provided a Q6_K quantized version of the model alongside a BF16 GGUF that can be fed into llama-quantize to create other quantizations as desired.

Below are two images demonstrating the output of both the Qwen 3.6 27B base model and this finetuned model for the same question. Both outputs were generated with a Q6_K quantization of each model on the same GPU.

Qwen 3.6 27B base model:

Qwen 3.6 27B Opus finetuned model:

Downloads last month: 31

GGUF

Model size

27B params

Architecture

qwen35

Hardware compatibility

6-bit

16-bit

Inference Providers NEW

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

Model tree for Gogeta70/Qwen_3.6_27B_Opus

Base model

Qwen/Qwen3.6-27B

Quantized

(708)

this model

Gogeta70
/

Qwen_3.6_27B_Opus

Model tree for Gogeta70/Qwen_3.6_27B_Opus

Dataset used to train Gogeta70/Qwen_3.6_27B_Opus