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"

NotHereNorThere commited on Jul 30

Commit

a4ec5d9

verified ·

1 Parent(s): 87fabea

Update README.md

Browse files

Files changed (1) hide show

README.md +15 -7

README.md CHANGED Viewed

@@ -12,10 +12,9 @@ tags:
 - TIES
 - qlora
 - unsloth
 ---
-model files soon im running the training run while typing this
 ### better late than never?
 > i made the base model a few months ago and never got around to finishing it.
@@ -30,10 +29,19 @@ to the like 12 people who downloaded the other Coral models, first of all thanks
 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
-# performance info coming ~~soon~~ eventually
-# quant guide coming ~~soon~~ eventually maybe

 - TIES
 - qlora
 - unsloth
+- uncensored
 ---
 ### better late than never?
 > i made the base model a few months ago and never got around to finishing it.
 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