Instructions to use MaliosDark/Nexus_Erebus_9B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MaliosDark/Nexus_Erebus_9B with Transformers:

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

pipe = pipeline("text-generation", model="MaliosDark/Nexus_Erebus_9B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MaliosDark/Nexus_Erebus_9B")
model = AutoModelForCausalLM.from_pretrained("MaliosDark/Nexus_Erebus_9B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

llama-cpp-python

How to use MaliosDark/Nexus_Erebus_9B with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="MaliosDark/Nexus_Erebus_9B",
	filename="nexus_erebus_9b.Q6_K.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 MaliosDark/Nexus_Erebus_9B 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 MaliosDark/Nexus_Erebus_9B:Q6_K
# Run inference directly in the terminal:
llama cli -hf MaliosDark/Nexus_Erebus_9B:Q6_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf MaliosDark/Nexus_Erebus_9B:Q6_K
# Run inference directly in the terminal:
llama cli -hf MaliosDark/Nexus_Erebus_9B:Q6_K

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 MaliosDark/Nexus_Erebus_9B:Q6_K
# Run inference directly in the terminal:
./llama-cli -hf MaliosDark/Nexus_Erebus_9B:Q6_K

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 MaliosDark/Nexus_Erebus_9B:Q6_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf MaliosDark/Nexus_Erebus_9B:Q6_K

Use Docker

docker model run hf.co/MaliosDark/Nexus_Erebus_9B:Q6_K

LM Studio
Jan

vLLM

How to use MaliosDark/Nexus_Erebus_9B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MaliosDark/Nexus_Erebus_9B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MaliosDark/Nexus_Erebus_9B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/MaliosDark/Nexus_Erebus_9B:Q6_K

SGLang

How to use MaliosDark/Nexus_Erebus_9B 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 "MaliosDark/Nexus_Erebus_9B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MaliosDark/Nexus_Erebus_9B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "MaliosDark/Nexus_Erebus_9B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MaliosDark/Nexus_Erebus_9B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use MaliosDark/Nexus_Erebus_9B with Ollama:
```
ollama run hf.co/MaliosDark/Nexus_Erebus_9B:Q6_K
```

Unsloth Studio

How to use MaliosDark/Nexus_Erebus_9B 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 MaliosDark/Nexus_Erebus_9B 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 MaliosDark/Nexus_Erebus_9B to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for MaliosDark/Nexus_Erebus_9B to start chatting

How to use MaliosDark/Nexus_Erebus_9B with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf MaliosDark/Nexus_Erebus_9B:Q6_K

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": "MaliosDark/Nexus_Erebus_9B:Q6_K"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use MaliosDark/Nexus_Erebus_9B with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf MaliosDark/Nexus_Erebus_9B:Q6_K

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 MaliosDark/Nexus_Erebus_9B:Q6_K

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use MaliosDark/Nexus_Erebus_9B with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf MaliosDark/Nexus_Erebus_9B:Q6_K

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 "MaliosDark/Nexus_Erebus_9B:Q6_K" \
  --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"

Docker Model Runner
How to use MaliosDark/Nexus_Erebus_9B with Docker Model Runner:
```
docker model run hf.co/MaliosDark/Nexus_Erebus_9B:Q6_K
```

Lemonade

How to use MaliosDark/Nexus_Erebus_9B with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull MaliosDark/Nexus_Erebus_9B:Q6_K

Run and chat with the model

lemonade run user.Nexus_Erebus_9B-Q6_K

List all available models

lemonade list

Nexus_Erebus_9B

Nexus_Erebus_9B is a code-focused fine-tune of Qwen3.5-9B, trained with the Isabel method (targeted high-quality data → benchmark → iterate) to become one of the strongest programming models in its size class. It is developed by Ideoa Labs.

This is v1 (code-focused). A balanced v2 (code + math + reasoning, designed so nothing regresses) is in preparation.

Honesty note. The numbers and limitations below are real, measured on this exact checkpoint. Nothing is inflated. Where the model is weak, it says so.

What it is

Base: Qwen/Qwen3.5-9B (2026 hybrid architecture, model_type: qwen3_5_text)
Method: QLoRA (4-bit NF4, double quant, bf16 compute) + LoRA r=16, alpha=16, target_modules="all-linear", merged back into fp16 weights for release.
Focus: Python code generation and algorithmic problem solving.

Training data

Source	Purpose
`nvidia/OpenCodeInstruct` (test-score filtered ≥ 0.5)	High-quality code instruction/solution pairs
`open-r1/OpenR1-Math-220k`	Mathematical reasoning traces
`ansulev/claude_mythos_distilled_25k`	Claude-style step-by-step reasoning

Trained for 1 epoch, cosine schedule, paged_adamw_8bit, sequence length 1024.

Benchmarks

Measured via ollama (Q6_K GGUF), greedy decoding, first 50 problems of each set, pass@1.

Benchmark	Nexus_Erebus_9B	Notes
HumanEval	80.0%	Code generation, pass@1
MBPP	68.0%	Code generation, pass@1
GSM8K	38.0%	Grade-school math (see limitations)

HumanEval reference points

Where Nexus_Erebus_9B (80.0%) sits among known models on HumanEval:

Model	HumanEval pass@1
GPT-4	~90%
Qwen2.5-Coder-7B	~88%
Nexus_Erebus_9B	80.0%
DeepSeek-Coder-6.7B	~78%
Llama-3-8B	~62%
GPT-3.5	~48%

Hard-problem stress test

Beyond aggregate benchmarks, the model was tested on individual LeetCode Hard problems, running its raw output against reference solutions over hundreds of random + edge cases, with no hints or fixes:

Problem	Result
Median of Two Sorted Arrays (O(log))	PASS (binary search on smaller array)
Regular Expression Matching (`.`, `*`)	PASS (DP table)
Edit Distance	PASS
Longest Valid Parentheses	PASS (stack + sentinel index)
Word Break II	PASS (backtracking)
Nth Ugly Number	PASS (three-pointer DP)
Count of Smaller Numbers After Self	PASS
Russian Doll Envelopes	PASS (LIS + height-descending tie-break)
Shortest Path Visiting All Nodes (bitmask)	FAIL (chose DFS+memo, infinite recursion)

Strength: implementing known algorithms, including the subtle optimal tricks, is excellent. Ceiling: paradigm selection and self-verification on unfamiliar problems (e.g. choosing BFS over DFS for a state-space shortest path). This is the same root as the softer math score, and is the explicit target of the upcoming balanced v2.

Usage

transformers (requires `transformers >= 5.2`)

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "MaliosDark/Nexus_Erebus_9B"
tok = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", dtype="bfloat16")

messages = [{"role": "user", "content": "Write a Python function that returns the median of two sorted arrays in O(log(m+n))."}]
inputs = tok.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(model.device)
out = model.generate(inputs, max_new_tokens=512, temperature=0)
print(tok.decode(out[0][inputs.shape[-1]:], skip_special_tokens=True))

The Qwen3.5 architecture needs transformers >= 5.2 (plus torchvision, pillow, causal_conv1d, and flash-linear-attention for the hybrid/linear-attention kernels).

GGUF (llama.cpp / Ollama)

A Q6_K GGUF quantization is included in this repo (nexus_erebus_9b.Q6_K.gguf).

ollama create nexus_erebus_9b -f Modelfile   # Modelfile: FROM ./nexus_erebus_9b.Q6_K.gguf
ollama run nexus_erebus_9b "Write a Python LRU cache."

For best results on code, prefix prompts with /no_think.

Files

model.safetensors, config.json, tokenizer files: full fp16 model (transformers).
nexus_erebus_9b.Q6_K.gguf: quantized weights for llama.cpp / Ollama.
adapter/: the raw LoRA adapter, for reproducibility.

Limitations

Math / multi-step reasoning is the weak point (GSM8K 38%). Prefer it for code, not arithmetic word problems.
Paradigm choice on novel problems can be wrong (see stress test); it may confidently pick a flawed approach and not self-correct.
Inherits the biases and knowledge cutoff of the Qwen3.5-9B base.
.generate() on some hybrid configs can be finicky; the GGUF path (llama.cpp/Ollama) is the most robust for inference.

License

Released under Apache-2.0, following the base Qwen/Qwen3.5-9B license. You are responsible for complying with the base model's terms.

Citation

@misc{nexus_erebus_9b_2026,
  title  = {Nexus_Erebus_9B: A Code-Focused Fine-Tune of Qwen3.5-9B},
  author = {Andryu Schittone},
  year   = {2026},
  publisher = {Ideoa Labs},
  howpublished = {\url{https://huggingface.co/MaliosDark/Nexus_Erebus_9B}}
}

Built by Ideoa Labs.

Downloads last month: 26

Safetensors

Model size

9B params

Tensor type

F16

Model tree for MaliosDark/Nexus_Erebus_9B

Base model

Qwen/Qwen3.5-9B-Base

Finetuned

Qwen/Qwen3.5-9B

Quantized

(354)

this model

Nexus_Erebus_9B

What it is

Training data

Benchmarks

HumanEval reference points

Hard-problem stress test

Usage

transformers (requires transformers >= 5.2)

GGUF (llama.cpp / Ollama)

Files

Limitations

License

Citation

Model tree for MaliosDark/Nexus_Erebus_9B

transformers (requires `transformers >= 5.2`)