Instructions to use NotHereNorThere/Coral-v1.5-0.6B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NotHereNorThere/Coral-v1.5-0.6B with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="NotHereNorThere/Coral-v1.5-0.6B",
	filename="Q3_K_L.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use NotHereNorThere/Coral-v1.5-0.6B with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf NotHereNorThere/Coral-v1.5-0.6B:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf NotHereNorThere/Coral-v1.5-0.6B:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf NotHereNorThere/Coral-v1.5-0.6B:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf NotHereNorThere/Coral-v1.5-0.6B: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 NotHereNorThere/Coral-v1.5-0.6B:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf NotHereNorThere/Coral-v1.5-0.6B: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 NotHereNorThere/Coral-v1.5-0.6B:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf NotHereNorThere/Coral-v1.5-0.6B:Q4_K_M

Use Docker

docker model run hf.co/NotHereNorThere/Coral-v1.5-0.6B:Q4_K_M

LM Studio
Jan

vLLM

How to use NotHereNorThere/Coral-v1.5-0.6B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "NotHereNorThere/Coral-v1.5-0.6B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NotHereNorThere/Coral-v1.5-0.6B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/NotHereNorThere/Coral-v1.5-0.6B:Q4_K_M

Ollama
How to use NotHereNorThere/Coral-v1.5-0.6B with Ollama:
```
ollama run hf.co/NotHereNorThere/Coral-v1.5-0.6B:Q4_K_M
```

Unsloth Studio

How to use NotHereNorThere/Coral-v1.5-0.6B 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 NotHereNorThere/Coral-v1.5-0.6B 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 NotHereNorThere/Coral-v1.5-0.6B to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for NotHereNorThere/Coral-v1.5-0.6B to start chatting

How to use NotHereNorThere/Coral-v1.5-0.6B with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf NotHereNorThere/Coral-v1.5-0.6B:Q4_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": "NotHereNorThere/Coral-v1.5-0.6B:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use NotHereNorThere/Coral-v1.5-0.6B with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf NotHereNorThere/Coral-v1.5-0.6B: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 NotHereNorThere/Coral-v1.5-0.6B:Q4_K_M

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use NotHereNorThere/Coral-v1.5-0.6B with Docker Model Runner:
```
docker model run hf.co/NotHereNorThere/Coral-v1.5-0.6B:Q4_K_M
```

Lemonade

How to use NotHereNorThere/Coral-v1.5-0.6B with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull NotHereNorThere/Coral-v1.5-0.6B:Q4_K_M

Run and chat with the model

lemonade run user.Coral-v1.5-0.6B-Q4_K_M

List all available models

lemonade list

Coral-v1.5-0.6B by NotHereNorThere

A 0.6B parameter uncensored generalist with adaptive Chain-of-Thought reasoning, it decides on its own whether a question needs thinking or not. Built from a 5-donor TIES merge of Qwen3-0.6B finetunes, healed with a 1k row fine-tune pass.

Part of the Coral-v1.5 model family, which adds to the original CoralLM series (Llama 3.2 1B based). Coral-v1.5 moves to Qwen3 architecture for native <think> support and significantly improved base capability.

What makes it interesting

Adaptive CoT at 0.6B — the model routes dynamically: simple questions get instant answers, complex reasoning tasks trigger <think> blocks. This accidently emerged from the fine-tune data mix rather than being explicitly trained.
Uncensored — refusal behavior has been removed via two abliterated donors. It just answers things.
Correct arithmetic — passes basic math with clean step-by-step working.

Merge Recipe

Method: TIES
Base: Qwen/Qwen3-0.6B
Tool: mergekit

Donor	Role	Weight	Density
`reaperdoesntknow/Qwen3-0.6B-Distilled-30B-A3B-Thinking-SFT`	Thinking / reasoning	0.30	0.5
`MihaiPopa-1/Qwen-3-0.6B-Claude-4.7-Opus-Distilled`	Claude-style CoT	0.30	0.5
`suayptalha/Qwen3-0.6B-Code-Expert`	Code	0.25	0.5
`DavidAU/Qwen3-0.6B-heretic-abliterated-uncensored`	De-alignment	0.15	0.5
`huihui-ai/Huihui-Qwen3-0.6B-abliterated-v2`	De-alignment	0.15	0.5

base_model: Qwen/Qwen3-0.6B
merge_method: ties
dtype: bfloat16
parameters:
  normalize: true
  int8_mask: true

Fine-tune

Post-merge heal pass to fix coherence, identity, counting, and context retention. Also reinforces when to use CoT vs when to answer directly.

500 rows — OpenHermes 2.5 (simple QA + instruction following)
500 rows — OpenThoughts (reasoning with CoT)
Method: QLoRA + Flash Attention 2
Total: 1,000 rows, randomly sampled and shuffled

The 50/50 split between non-CoT and CoT data is seemingly what produced the adaptive routing behavior.

Evaluation

Tested post-heal on the following:

Test	Result
Basic greeting	✅ Clean, friendly, no loops
Identity	✅ Identifies as AI assistant
Exact instruction following ("list 3 fruits")	✅ Correct count and formatting
Context retention across turns	✅ Recalled user name correctly
Math (47 × 83)	✅ Correct (3,901) with clean working
Prime number function	✅ Correct implementation and examples
One-sentence explanation	✅ Stayed concise, no yapping
Adaptive CoT routing	✅ Emergent, skips think for simple, uses think for complex
Uncensored	✅ Refusals removed

Quant Guide

Quant	Quality
F16	Star of the show, best
Q6	Should match F16
Q5	Starts degrading
Q4	What could you run this on that's that bad
Q3	Don't

Downloads last month: 1,024

GGUF

Model size

0.6B params

Architecture

qwen3

Hardware compatibility

3-bit

4-bit

5-bit

6-bit

16-bit

Model tree for NotHereNorThere/Coral-v1.5-0.6B

Base model

Qwen/Qwen3-0.6B-Base

Finetuned

Qwen/Qwen3-0.6B

Quantized

(319)

this model

Datasets used to train NotHereNorThere/Coral-v1.5-0.6B

Collection including NotHereNorThere/Coral-v1.5-0.6B

Coral

Collection

Merged models to combine strengths without retraining or heavy fine tuning. • 3 items • Updated 4 days ago