Instructions to use Joesh1/onca-2.0-12b-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 Joesh1/onca-2.0-12b-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 Joesh1/onca-2.0-12b-gguf:BF16
# Run inference directly in the terminal:
llama cli -hf Joesh1/onca-2.0-12b-gguf:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Joesh1/onca-2.0-12b-gguf:BF16
# Run inference directly in the terminal:
llama cli -hf Joesh1/onca-2.0-12b-gguf: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 Joesh1/onca-2.0-12b-gguf:BF16
# Run inference directly in the terminal:
./llama-cli -hf Joesh1/onca-2.0-12b-gguf: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 Joesh1/onca-2.0-12b-gguf:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Joesh1/onca-2.0-12b-gguf:BF16

Use Docker

docker model run hf.co/Joesh1/onca-2.0-12b-gguf:BF16

LM Studio
Jan

vLLM

How to use Joesh1/onca-2.0-12b-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Joesh1/onca-2.0-12b-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": "Joesh1/onca-2.0-12b-gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Joesh1/onca-2.0-12b-gguf:BF16

Ollama
How to use Joesh1/onca-2.0-12b-gguf with Ollama:
```
ollama run hf.co/Joesh1/onca-2.0-12b-gguf:BF16
```

Unsloth Studio

How to use Joesh1/onca-2.0-12b-gguf 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 Joesh1/onca-2.0-12b-gguf 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 Joesh1/onca-2.0-12b-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Joesh1/onca-2.0-12b-gguf to start chatting

How to use Joesh1/onca-2.0-12b-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Joesh1/onca-2.0-12b-gguf: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": "Joesh1/onca-2.0-12b-gguf:BF16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use Joesh1/onca-2.0-12b-gguf with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Joesh1/onca-2.0-12b-gguf: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 "Joesh1/onca-2.0-12b-gguf: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"

Docker Model Runner
How to use Joesh1/onca-2.0-12b-gguf with Docker Model Runner:
```
docker model run hf.co/Joesh1/onca-2.0-12b-gguf:BF16
```

Lemonade

How to use Joesh1/onca-2.0-12b-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Joesh1/onca-2.0-12b-gguf:BF16

Run and chat with the model

lemonade run user.onca-2.0-12b-gguf-BF16

List all available models

lemonade list

Hermes Agent

How to use Joesh1/onca-2.0-12b-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 Joesh1/onca-2.0-12b-gguf: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 Joesh1/onca-2.0-12b-gguf:BF16

Run Hermes

hermes

Atomic Chat

ONCA 2.0 12B GGUF

ONCA 2.0 four-task primary-holdout comparison

_{BF16 reference scores on the unchanged 1,309-example primary holdout; compare values within each task panel.}

Summary

ONCA 2.0 is an open oncology language model for trial screening, clinical reasoning, pathology extraction, and variant evidence interpretation. It builds on google/gemma-4-12B-it with continued supervised fine-tuning on a provenance-labeled oncology corpus while retaining the four-task ONCA 1.5 evaluation contract.

This page provides BF16, Q8_0, Q6_K, and Q4_K_M GGUF files generated from the merged ONCA 2.0 checkpoint. All variants are collected here so users can choose the precision and memory tier suited to their hardware.

At a Glance

Model file	Quantization	Size	Memory tier	Best for
`onca-2.0-12b-bf16-gguf.gguf`	BF16	23.8 GB	Highest	Maximum fidelity
`onca-2.0-12b-int8-gguf.gguf`	Q8_0	12.7 GB	High	Near-full precision quality
`onca-2.0-12b-int6-gguf.gguf`	Q6_K	9.8 GB	Medium	Quality/size balance
`onca-2.0-12b-int4-gguf.gguf`	Q4_K_M	7.4 GB	Lowest	Constrained hardware

Field	Value
Base model	`google/gemma-4-12B-it`
Runtime	llama.cpp with Gemma 4 support
Context window	262,144 tokens
Domain focus	Pancreatic cancer and oncology research
Validation	All four artifacts passed load and generation smoke tests

Quick Start

Use a recent llama.cpp build with Gemma 4 support. The Q4_K_M file is a practical starting point for lower-memory systems.

llama-cli \
  -m onca-2.0-12b-int4-gguf.gguf \
  -cnv \
  -p 'Patient: metastatic pancreatic adenocarcinoma; ECOG 1. Trial: metastatic PDAC, ECOG 0-1. Return JSON with keys eligible, reason, and missing_information.'

Replace the model path with the BF16, Q8_0, or Q6_K file when more memory and higher fidelity are available. Checksums and validation details are recorded in verification_20260716.json.

Training Scope

The source BF16 checkpoint was trained on 25,302 examples. Validation, test, and primary-holdout sets retain the ONCA 1.5 four-task evaluation contract.

Task family	Train	Original	Generated	Val	Test	Holdout
Trial Screening	10,921	10,921	0	608	608	608
Clinical Reasoning	3,647	3,146	501	174	176	176
Pathology Extraction	4,559	333	4,226	410	400	400
Variant Evidence	6,175	2,191	3,984	116	125	125
Total	25,302	16,591	8,711	1,308	1,309	1,309

Related Releases

onca-2.0-12B: BF16 Transformers reference release.
onca-2.0-12B-INT8: 8-bit BitsAndBytes release.
onca-2.0-12B-INT4: 4-bit BitsAndBytes release.
onca-2.0-12B-GGUF: combined GGUF collection (this page).

Limitations

This is a research model, not a clinical decision system.
Outputs require review by qualified experts before real-world use.
Structured or parser-valid output does not guarantee factual correctness.
The benchmark figure reports the BF16 reference checkpoint; individual GGUF quantizations were not fully rebenchmarked.
Lower-bit quantization can change output quality and behavior.

Citation

A formal ONCA 2.0 citation will be added with the accompanying manuscript. Until then, cite this model repository, the exact GGUF file, and its quantization.

Acknowledgements

ONCA 2.0 continues the ONCA project lineage and builds on Google Gemma, llama.cpp, and the open-data contributors whose datasets supported training and evaluation.