Instructions to use King3Djbl/nexus-science-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use King3Djbl/nexus-science-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="King3Djbl/nexus-science-GGUF")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("King3Djbl/nexus-science-GGUF", dtype="auto")

llama-cpp-python

How to use King3Djbl/nexus-science-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="King3Djbl/nexus-science-GGUF",
	filename="nexus-science-f16.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use King3Djbl/nexus-science-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 King3Djbl/nexus-science-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf King3Djbl/nexus-science-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 King3Djbl/nexus-science-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf King3Djbl/nexus-science-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 King3Djbl/nexus-science-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf King3Djbl/nexus-science-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 King3Djbl/nexus-science-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf King3Djbl/nexus-science-GGUF:Q4_K_M

Use Docker

docker model run hf.co/King3Djbl/nexus-science-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use King3Djbl/nexus-science-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "King3Djbl/nexus-science-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "King3Djbl/nexus-science-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/King3Djbl/nexus-science-GGUF:Q4_K_M

SGLang

How to use King3Djbl/nexus-science-GGUF with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "King3Djbl/nexus-science-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "King3Djbl/nexus-science-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "King3Djbl/nexus-science-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "King3Djbl/nexus-science-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use King3Djbl/nexus-science-GGUF with Ollama:
```
ollama run hf.co/King3Djbl/nexus-science-GGUF:Q4_K_M
```

Unsloth Studio

How to use King3Djbl/nexus-science-GGUF 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 King3Djbl/nexus-science-GGUF 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 King3Djbl/nexus-science-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for King3Djbl/nexus-science-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use King3Djbl/nexus-science-GGUF with Docker Model Runner:
```
docker model run hf.co/King3Djbl/nexus-science-GGUF:Q4_K_M
```

Lemonade

How to use King3Djbl/nexus-science-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull King3Djbl/nexus-science-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.nexus-science-GGUF-Q4_K_M

List all available models

lemonade list

nexus-science-GGUF

NEXUS domain specialist for scientific reasoning and research — lightweight & uncensored.

Base model: fableforge-ai/NEXUS-Science · Part of the FableForge ecosystem.

🏆 Benchmarks — 140/150 (93%)

A 1.5B model scoring 93% — punching far above its weight. 30-prompt evaluation (domain knowledge, uncensored domain + general, reasoning, tool use), 0–5 scoring, run on an NVIDIA A40 via Ollama.

Category	Score	Avg
🎯 Domain Knowledge	47/50	4.7/5
🔓 Uncensored (Domain)	25/25	5.0/5
🔓 Uncensored (General)	22/25	4.4/5
🧠 Reasoning	25/25	5.0/5
🔧 Tool Use	21/25	4.2/5
Total	140/150	93%

🧬 The NEXUS Family — six specialists, one tiny footprint

Model	Score	Specialty
NEXUS-Coder	141/150	Software Engineering & Code
NEXUS-Security	144/150	Cybersecurity & Hacking
NEXUS-Medical	140/150	Medicine & Healthcare
NEXUS-Legal	139/150	Law & Compliance
NEXUS-Finance	144/150	Finance & Accounting
NEXUS-Science	140/150	Science & Research

👉 Grab the whole family on Ollama or Hugging Face.

⚡ Quickest start — Ollama (these pulls credit the source, not a mirror)

ollama run fableforge-ai/nexus-science:q4_k_m   # published on ollama.com
ollama run hf.co/King3Djbl/nexus-science-GGUF:Q4_K_M

🦙 llama.cpp

llama-cli -hf King3Djbl/nexus-science-GGUF:Q4_K_M -p "Hello!"

💠 LM Studio

Search King3Djbl/nexus-science-GGUF and pick a quant below.

📦 Provided quants (download one file, not the whole repo)

File	Quant	Size	Notes
nexus-science-f16.gguf	`F16`	3.09 GB	Full precision (unquantized). Reference / conversion.
nexus-science-q8_0.gguf	`Q8_0`	1.65 GB	Extremely high quality — usually overkill.
nexus-science-q6_k.gguf	`Q6_K`	1.27 GB	Very high quality, near-perfect. Recommended if you have the RAM.
nexus-science-q5_k_m.gguf	`Q5_K_M`	1.13 GB	High quality. Recommended.
nexus-science-q4_k_m.gguf	`Q4_K_M`	0.99 GB	⭐ Best size/quality balance — default pick for most users.
nexus-science-iq4_xs.gguf	`IQ4_XS`	0.90 GB	imatrix — great quality, smaller than Q4_K_S. Recommended for low RAM.
nexus-science-q4_0.gguf	`Q4_0`	0.94 GB	Legacy format — prefer Q4_K_M.
nexus-science-q3_k_m.gguf	`Q3_K_M`	0.82 GB	Lower quality; usable when RAM is tight.
nexus-science-iq3_xxs.gguf	`IQ3_XXS`	0.67 GB	imatrix very low quality.
nexus-science-q2_k.gguf	`Q2_K`	0.68 GB	Very low quality — surprisingly usable.
nexus-science-iq2_xxs.gguf	`IQ2_XXS`	0.51 GB	Tiny imatrix — last resort.

Not sure? Take Q4_K_M. Low RAM → IQ4_XS. Max quality → Q6_K.

🧠 Prompt format (ChatML)

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

🌌 See it live — the FableForge demos

This family powers a galaxy of free, interactive HF Spaces:

⭐ Like & share — it helps people find the source instead of a mirror.

Downloads last month: 51

GGUF

Model size

2B params

Architecture

qwen2

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Model tree for King3Djbl/nexus-science-GGUF

Base model

Qwen/Qwen2.5-1.5B

Finetuned

Qwen/Qwen2.5-1.5B-Instruct

Finetuned

fableforge-ai/NEXUS-Science

Quantized

(1)

this model