Instructions to use jabbatheduck/oscar2-models with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jabbatheduck/oscar2-models with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="jabbatheduck/oscar2-models",
	filename="qwen3.6-27b-q5kxl-hadamard.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 jabbatheduck/oscar2-models 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 jabbatheduck/oscar2-models
# Run inference directly in the terminal:
llama cli -hf jabbatheduck/oscar2-models

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf jabbatheduck/oscar2-models
# Run inference directly in the terminal:
llama cli -hf jabbatheduck/oscar2-models

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 jabbatheduck/oscar2-models
# Run inference directly in the terminal:
./llama-cli -hf jabbatheduck/oscar2-models

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 jabbatheduck/oscar2-models
# Run inference directly in the terminal:
./build/bin/llama-cli -hf jabbatheduck/oscar2-models

Use Docker

docker model run hf.co/jabbatheduck/oscar2-models

LM Studio
Jan
Ollama
How to use jabbatheduck/oscar2-models with Ollama:
```
ollama run hf.co/jabbatheduck/oscar2-models
```

Unsloth Studio

How to use jabbatheduck/oscar2-models 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 jabbatheduck/oscar2-models 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 jabbatheduck/oscar2-models to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for jabbatheduck/oscar2-models to start chatting

How to use jabbatheduck/oscar2-models with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf jabbatheduck/oscar2-models

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": "jabbatheduck/oscar2-models"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use jabbatheduck/oscar2-models with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf jabbatheduck/oscar2-models

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 jabbatheduck/oscar2-models

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use jabbatheduck/oscar2-models with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf jabbatheduck/oscar2-models

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 "jabbatheduck/oscar2-models" \
  --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 jabbatheduck/oscar2-models with Docker Model Runner:
```
docker model run hf.co/jabbatheduck/oscar2-models
```

Lemonade

How to use jabbatheduck/oscar2-models with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull jabbatheduck/oscar2-models

Run and chat with the model

lemonade run user.oscar2-models-{{QUANT_TAG}}

List all available models

lemonade list

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

OSCAR2 Models

Collection: OSCAR2 Models

Model

Name	File	KV cache	Context
Qwen3.6-27B-Q5KXL-Hadamard	`qwen3.6-27b-q5kxl-hadamard.gguf`	oscar2/oscar2	131072

OSCAR2 Source

This model requires an oscar2-capable build of llama.cpp from the TurboQuant oscar branch.

Repo: https://github.com/giveen/llama-cpp-turboquant
Branch: oscar

Build Instructions

git clone -b oscar https://github.com/giveen/llama-cpp-turboquant.git
cd llama-cpp-turboquant
mkdir build && cd build
cmake .. -DCMAKE_BUILD_TYPE=Release -DGGML_CUDA=ON
cmake --build . --config Release -j $(nproc)

Run with this Model

./build/bin/llama-cli \
  -m /path/to/qwen3.6-27b-q5kxl-hadamard.gguf \
  -ngl 99 -fa on -c 131072 \
  --cache-type-k oscar2 --cache-type-v oscar2 \
  -n 512 --temp 0

Notes

Requires NVIDIA Blackwell GPU with CUDA 13.3 or compatible.
KV cache stores ~2.25 bits/weight with oscar2 quantization.
Use --no-jinja if chat template parsing fails with very long prompts.

Downloads last month: -

GGUF

Model size

27B params

Architecture

qwen35

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Inference Providers NEW

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

Collection including jabbatheduck/oscar2-models

OSCAR2 Models

Collection

1 item • Updated about 21 hours ago