Instructions to use prithivMLmods/elephant-1-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use prithivMLmods/elephant-1-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-classification", model="prithivMLmods/elephant-1-GGUF")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("prithivMLmods/elephant-1-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use prithivMLmods/elephant-1-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 prithivMLmods/elephant-1-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf prithivMLmods/elephant-1-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf prithivMLmods/elephant-1-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf prithivMLmods/elephant-1-GGUF:Q4_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 prithivMLmods/elephant-1-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf prithivMLmods/elephant-1-GGUF:Q4_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 prithivMLmods/elephant-1-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf prithivMLmods/elephant-1-GGUF:Q4_K_M

Use Docker

docker model run hf.co/prithivMLmods/elephant-1-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use prithivMLmods/elephant-1-GGUF with Ollama:
```
ollama run hf.co/prithivMLmods/elephant-1-GGUF:Q4_K_M
```
Unsloth Desktop

How to use prithivMLmods/elephant-1-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf prithivMLmods/elephant-1-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "prithivMLmods/elephant-1-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use prithivMLmods/elephant-1-GGUF with Docker Model Runner:
```
docker model run hf.co/prithivMLmods/elephant-1-GGUF:Q4_K_M
```

Lemonade

How to use prithivMLmods/elephant-1-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull prithivMLmods/elephant-1-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.elephant-1-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use prithivMLmods/elephant-1-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 prithivMLmods/elephant-1-GGUF:Q4_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 prithivMLmods/elephant-1-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use prithivMLmods/elephant-1-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf prithivMLmods/elephant-1-GGUF:Q4_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 "prithivMLmods/elephant-1-GGUF:Q4_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"

elephant-1-GGUF

elephant-1 is an MIT-licensed, 9B-parameter decision model developed by Base Labs at Baseten by fully fine-tuning Qwen3.5-9B (with a frozen vision encoder) on 6.21 million decision examples for classification, routing, and guardrail tasks. Utilizing a block-bidirectional mask on full-attention layers and a 16,384-token context window, the model evaluates an input state against multiple binary (noul), categorical (choice), and ordinal (score) questions simultaneously in a single shared-prefix prefill pass to output well-calibrated probabilities for every option. Trained across 128 H100 GPUs using cross-entropy paired with a Brier calibration objective and a built-in abstention option, elephant-1 ranks as the best model under 15B parameters on the Jev Decision Index 0.4 (scoring 62.65) and achieves 65.2 on the Artificial Analysis Decision Index replica, offering a lightweight, high-efficiency alternative to its larger 27B sibling, mammoth-1.

MTP — Speculative Decoding: No

Model Files

File Name	Quant Type	File Size	File Link	Description
elephant-1.BF16.gguf	BF16	17.9 GB	Link	Full BF16 weights. Highest quality, largest file size.
elephant-1.Q3_K_L.gguf	Q3_K_L	4.93 GB	Link	Lower quality but usable, good for low RAM availability.
elephant-1.Q4_K_M.gguf	Q4_K_M	5.63 GB	Link	Good quality, default size for most use cases, recommended.
elephant-1.Q5_K_M.gguf	Q5_K_M	6.47 GB	Link	High quality, recommended.
elephant-1.Q6_K.gguf	Q6_K	7.36 GB	Link	Very high quality, near perfect, recommended.
elephant-1.mmproj-bf16.gguf	mmproj-bf16	922 MB	Link	Multimodal projection file in BF16 format. Used for vision/language models.