Instructions to use krishnakartik/gemma4-social-bias-judge-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 krishnakartik/gemma4-social-bias-judge-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 krishnakartik/gemma4-social-bias-judge-gguf:Q5_K_M
# Run inference directly in the terminal:
llama cli -hf krishnakartik/gemma4-social-bias-judge-gguf:Q5_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf krishnakartik/gemma4-social-bias-judge-gguf:Q5_K_M
# Run inference directly in the terminal:
llama cli -hf krishnakartik/gemma4-social-bias-judge-gguf:Q5_K_M

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 krishnakartik/gemma4-social-bias-judge-gguf:Q5_K_M
# Run inference directly in the terminal:
./llama-cli -hf krishnakartik/gemma4-social-bias-judge-gguf:Q5_K_M

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 krishnakartik/gemma4-social-bias-judge-gguf:Q5_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf krishnakartik/gemma4-social-bias-judge-gguf:Q5_K_M

Use Docker

docker model run hf.co/krishnakartik/gemma4-social-bias-judge-gguf:Q5_K_M

LM Studio
Jan
Ollama
How to use krishnakartik/gemma4-social-bias-judge-gguf with Ollama:
```
ollama run hf.co/krishnakartik/gemma4-social-bias-judge-gguf:Q5_K_M
```

Unsloth Studio

How to use krishnakartik/gemma4-social-bias-judge-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 krishnakartik/gemma4-social-bias-judge-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 krishnakartik/gemma4-social-bias-judge-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for krishnakartik/gemma4-social-bias-judge-gguf to start chatting

How to use krishnakartik/gemma4-social-bias-judge-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf krishnakartik/gemma4-social-bias-judge-gguf:Q5_K_M

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": "krishnakartik/gemma4-social-bias-judge-gguf:Q5_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use krishnakartik/gemma4-social-bias-judge-gguf with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf krishnakartik/gemma4-social-bias-judge-gguf:Q5_K_M

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 "krishnakartik/gemma4-social-bias-judge-gguf:Q5_K_M" \
  --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 krishnakartik/gemma4-social-bias-judge-gguf with Docker Model Runner:
```
docker model run hf.co/krishnakartik/gemma4-social-bias-judge-gguf:Q5_K_M
```

Lemonade

How to use krishnakartik/gemma4-social-bias-judge-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull krishnakartik/gemma4-social-bias-judge-gguf:Q5_K_M

Run and chat with the model

lemonade run user.gemma4-social-bias-judge-gguf-Q5_K_M

List all available models

lemonade list

Hermes Agent

How to use krishnakartik/gemma4-social-bias-judge-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 krishnakartik/gemma4-social-bias-judge-gguf:Q5_K_M

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 krishnakartik/gemma4-social-bias-judge-gguf:Q5_K_M

Run Hermes

hermes

Atomic Chat

gemma4-social-bias-judge — GGUF quantizations

GGUF quantizations of the judge-from-scratch social-bias judge. Both the DPO primary release and the SFT-only secondary release are bundled in this single repo with suffixed Ollama tags so users can pick the right checkpoint for their use case from one discovery point.

Full model description, eval results, and the OOD-regression caveat that decides DPO vs SFT live in the model cards, not here:

DPO (default) — krishnakartik/gemma4-social-bias-judge
SFT-only — krishnakartik/gemma4-social-bias-judge-sft

⚠️ Important: Thinking Mode

These models were fine-tuned with Gemma 4's native thinking mode DISABLED. The bundled Modelfiles' SYSTEM blocks omit <|think|> deliberately. Do not modify them to enable thinking mode — see the primary model card for the full explanation.

Available tags

Tag	Checkpoint	Quant	File size	Use case
`:Q8_0`	DPO (default)	Q8_0	8.03 GB	Best quality; recommended starting point
`:Q5_K_M`	DPO	Q5_K_M	5.76 GB	Smaller; minor quality trade-off
`:Q8_0-sft`	SFT-only	Q8_0	8.03 GB	Use for OOD bias categories
`:Q5_K_M-sft`	SFT-only	Q5_K_M	5.76 GB	Smaller SFT-only

(Sizes are larger than typical 4B quantizations because Gemma 4 E4B has ~8B raw parameters even though it operates at "4B effective" via the per-layer-input embedding mechanism. Plan for the fp16-baseline equivalent of ~16 GB of disk.)

If your bias categories are outside BBQ's training set (politics, ideology, novel demographic axes), prefer the -sft tags — see the OOD-regression discussion on the primary model card.

Quick start

Ollama (default DPO Q8_0)

ollama run hf.co/krishnakartik/gemma4-social-bias-judge-gguf:Q8_0

Ollama (SFT-only Q8_0)

ollama run hf.co/krishnakartik/gemma4-social-bias-judge-gguf:Q8_0-sft

llama.cpp

The judge expects a specific system prompt; pull both the GGUF and the system-prompt text into a working directory before invoking llama-cli.

# 1. Pull the GGUF.
huggingface-cli download \
  krishnakartik/gemma4-social-bias-judge-gguf Q8_0.gguf \
  --local-dir ./gemma4-judge

# 2. Pull the system prompt (Apache-2.0; canonical source in the
#    judge-from-scratch repo).
curl -fsSL -o ./gemma4-judge/system_prompt.md \
  https://raw.githubusercontent.com/krishnakartik1/judge-from-scratch/main/data/judge_system_prompt.md

# 3. Run.
llama-cli -m ./gemma4-judge/Q8_0.gguf \
  --temp 0 --ctx-size 4096 \
  --system-prompt-file ./gemma4-judge/system_prompt.md

Ollama users can skip the system-prompt download — the Modelfiles in this repo (Modelfile.Q8_0 etc.) embed the judge system prompt and the temperature / num_ctx settings already, so ollama run hf.co/...:Q8_0 is fully self-contained.

License & citation

Same as the primary model card.

Downloads last month: 56

GGUF

Model size

8B params

Architecture

gemma4

Hardware compatibility

5-bit

8-bit

Inference Providers NEW

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

Model tree for krishnakartik/gemma4-social-bias-judge-gguf

Base model

google/gemma-4-E4B

Finetuned

google/gemma-4-E4B-it

Quantized

(320)

this model