Instructions to use NotHereNorThere/Coral-2-4b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use NotHereNorThere/Coral-2-4b 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 NotHereNorThere/Coral-2-4b:Q5_K_M
# Run inference directly in the terminal:
llama cli -hf NotHereNorThere/Coral-2-4b:Q5_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf NotHereNorThere/Coral-2-4b:Q5_K_M
# Run inference directly in the terminal:
llama cli -hf NotHereNorThere/Coral-2-4b: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 NotHereNorThere/Coral-2-4b:Q5_K_M
# Run inference directly in the terminal:
./llama-cli -hf NotHereNorThere/Coral-2-4b: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 NotHereNorThere/Coral-2-4b:Q5_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf NotHereNorThere/Coral-2-4b:Q5_K_M

Use Docker

docker model run hf.co/NotHereNorThere/Coral-2-4b:Q5_K_M

LM Studio
Jan
Ollama
How to use NotHereNorThere/Coral-2-4b with Ollama:
```
ollama run hf.co/NotHereNorThere/Coral-2-4b:Q5_K_M
```
Unsloth Desktop

How to use NotHereNorThere/Coral-2-4b with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf NotHereNorThere/Coral-2-4b:Q5_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": "NotHereNorThere/Coral-2-4b:Q5_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use NotHereNorThere/Coral-2-4b with Docker Model Runner:
```
docker model run hf.co/NotHereNorThere/Coral-2-4b:Q5_K_M
```

Lemonade

How to use NotHereNorThere/Coral-2-4b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull NotHereNorThere/Coral-2-4b:Q5_K_M

Run and chat with the model

lemonade run user.Coral-2-4b-Q5_K_M

List all available models

lemonade list

Hermes Agent

How to use NotHereNorThere/Coral-2-4b with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf NotHereNorThere/Coral-2-4b: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 NotHereNorThere/Coral-2-4b:Q5_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use NotHereNorThere/Coral-2-4b with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf NotHereNorThere/Coral-2-4b: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 "NotHereNorThere/Coral-2-4b: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"

better late than never?

i made the base model a few months ago and never got around to finishing it. initially i did post train it properly... but i switched to a subsection of dolphin-R1 for Coral 1.6 and 2.0, which seemed like a way better idea than mixing openthoughts and openhermes, to try and buff out dynamic hybrid reasoning since it wasnt actually intentional. only after i finished the training run on the base model did i realize that my entire fine tuning workflow didnt support thinking blocks. that explained a lot. i didn't feel like fixing it then so i kept the base model and training set for later to finish and here we are.

to the like 12 people who downloaded the other Coral models, first of all thanks, i did not expect a single download, actual feedback on the models would be appreciated.

a whole 4 billion paramaters!?

yes i know, what a goliath of a model (at least for the Coral family so far), but seriously it's nothing special

a TIES merge from several fine tunes of Qwen 3 4b.
- including the original and later updated checkpoint.
then a QLORA-merge trained on a subsection of dolphin-r1 to cement the CoT.

actual performance

it passed rigourorous vibe testing, given you use the correct infrerence/chat settings.
- keeps qwen 3 4b's chat settings.
no refusal, TIES has a habit of removing post training censorship.
unfortunatly, thinking got steamrolled (TIES again). it still outputs <think> formatting but theyre always empty.
normal 4b model limitations.

quant guide

bf16 / dont bother, just use;
Q5 / near lossless and fits in a lot of devices

Downloads last month: 21

GGUF

Model size

4B params

Architecture

qwen3

Hardware compatibility

5-bit

16-bit

Inference Providers NEW

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

Model tree for NotHereNorThere/Coral-2-4b

Base model

Qwen/Qwen3-4B-Base

Finetuned

Qwen/Qwen3-4B

Quantized

(314)

this model

Collection including NotHereNorThere/Coral-2-4b

Coral

Collection

Merged models to combine strengths without retraining or heavy fine tuning. • 5 items • Updated about 10 hours ago