Instructions to use Thox-ai/ThoxWave-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Thox-ai/ThoxWave-8B with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("dphn/dolphin-2.9-llama3-8b")
model = PeftModel.from_pretrained(base_model, "Thox-ai/ThoxWave-8B")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Thox-ai/ThoxWave-8B 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 Thox-ai/ThoxWave-8B:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Thox-ai/ThoxWave-8B:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Thox-ai/ThoxWave-8B:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Thox-ai/ThoxWave-8B: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 Thox-ai/ThoxWave-8B:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Thox-ai/ThoxWave-8B: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 Thox-ai/ThoxWave-8B:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Thox-ai/ThoxWave-8B:Q4_K_M

Use Docker

docker model run hf.co/Thox-ai/ThoxWave-8B:Q4_K_M

LM Studio
Jan

vLLM

How to use Thox-ai/ThoxWave-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Thox-ai/ThoxWave-8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Thox-ai/ThoxWave-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Thox-ai/ThoxWave-8B:Q4_K_M

Ollama
How to use Thox-ai/ThoxWave-8B with Ollama:
```
ollama run hf.co/Thox-ai/ThoxWave-8B:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use Thox-ai/ThoxWave-8B with Docker Model Runner:
```
docker model run hf.co/Thox-ai/ThoxWave-8B:Q4_K_M
```

Lemonade

How to use Thox-ai/ThoxWave-8B with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Thox-ai/ThoxWave-8B:Q4_K_M

Run and chat with the model

lemonade run user.ThoxWave-8B-Q4_K_M

List all available models

lemonade list

Atomic Chat

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Access to this THOX model is granted manually by THOX.ai LLC.

ThoxWave-8B

Your AI. Your Data. Your Rules.

THOX 'Wave' — mid-size chat LoRA on Dolphin-2.9-Llama3-8B (→ Meta-Llama-3-8B) with a bundled Q4_K_M GGUF.

What this is

Training base: dphn/dolphin-2.9-llama3-8b (a Llama-3-8B fine-tune) → upstream meta-llama/Meta-Llama-3-8B (Llama 3 Community License).
LoRA r=8, α=16; ctx 8192; ChatML template; bundled thoxwave-8b-Q4_K_M.gguf.
Meta Llama 3 license requires the derivative name to include 'Llama 3' and a 'Built with Meta Llama 3' notice — currently not satisfied; flagged for legal.
Gated (manual approval).

Intended use

On-device / edge text generation within the THOX stack. Not a safety-aligned public assistant unless deployed behind THOX guardrails.

Prompt / chat template

<|im_start|>system
{system}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

Usage

Transformers + PEFT

from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer
base = "meta-llama/Meta-Llama-3-8B"
adapter = "Thox-ai/ThoxWave-8B"
tok = AutoTokenizer.from_pretrained(base)
model = AutoModelForCausalLM.from_pretrained(base, device_map="auto")
model = PeftModel.from_pretrained(model, adapter)

Bundled GGUF (llama.cpp / Ollama)

huggingface-cli download Thox-ai/ThoxWave-8B --include '*.gguf' --local-dir ./ThoxWave-8B

Model tree for Thox-ai/ThoxWave-8B

Base model

meta-llama/Meta-Llama-3-8B

Adapter

(737)

this model

Thox-ai
/

ThoxWave-8B