Instructions to use efops/marziel-8b-custom with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use efops/marziel-8b-custom with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("efops/marziel-8b-custom")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

llama-cpp-python

How to use efops/marziel-8b-custom with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="efops/marziel-8b-custom",
	filename="marziel-v6-Q4_K_M.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use efops/marziel-8b-custom with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf efops/marziel-8b-custom:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf efops/marziel-8b-custom:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf efops/marziel-8b-custom:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf efops/marziel-8b-custom: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 efops/marziel-8b-custom:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf efops/marziel-8b-custom: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 efops/marziel-8b-custom:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf efops/marziel-8b-custom:Q4_K_M

Use Docker

docker model run hf.co/efops/marziel-8b-custom:Q4_K_M

LM Studio
Jan

vLLM

How to use efops/marziel-8b-custom with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/efops/marziel-8b-custom:Q4_K_M

Ollama
How to use efops/marziel-8b-custom with Ollama:
```
ollama run hf.co/efops/marziel-8b-custom:Q4_K_M
```

Unsloth Studio new

How to use efops/marziel-8b-custom 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 efops/marziel-8b-custom 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 efops/marziel-8b-custom to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for efops/marziel-8b-custom to start chatting

Pi new

How to use efops/marziel-8b-custom with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "efops/marziel-8b-custom"

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "efops/marziel-8b-custom"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use efops/marziel-8b-custom with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "efops/marziel-8b-custom"

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 efops/marziel-8b-custom

Run Hermes

hermes

MLX LM

How to use efops/marziel-8b-custom with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "efops/marziel-8b-custom"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "efops/marziel-8b-custom"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "efops/marziel-8b-custom",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Docker Model Runner
How to use efops/marziel-8b-custom with Docker Model Runner:
```
docker model run hf.co/efops/marziel-8b-custom:Q4_K_M
```

Lemonade

How to use efops/marziel-8b-custom with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull efops/marziel-8b-custom:Q4_K_M

Run and chat with the model

lemonade run user.marziel-8b-custom-Q4_K_M

List all available models

lemonade list

Marziel OS v1.0.1

Private AI Operating System — runs entirely on your hardware.

Install

pip install marziel==1.0.1
marziel serve

v1.0.1 — Marziel OS

AI Kernel

Persistent event loop with autonomous decision-making
3-Tier Memory: Working, Long-Term (AES-256), Episodic
Process Manager: Unix-like ps/top/kill
Task Scheduler for recurring tasks

MarzielFlow — 5-Component Adaptive Inference

Speculative Decoding with automatic fallback
T/Z Distribution Quantization (Normal/Student-t/Beta)
Adaptive Bit-Width: 2.88-bit avg across 32 layers
Fuzzy Logic Controller (Mamdani-style)
Attention Sink Cache: 75% memory savings

TurboQuant

PolarQuant + QJL 3-bit KV cache — 3x memory reduction.

Model Formats

Format	Size	Platform
GGUF Q4_K_M	4.8 GB	NVIDIA GPU, CPU
MLX 4-bit	4.5 GB	Apple Silicon
Safetensors	16 GB	Full precision

GGUF Usage

from llama_cpp import Llama
model = Llama.from_pretrained(
    repo_id="efops/marziel-8b-custom",
    filename="marziel-v6-Q4_K_M.gguf",
    n_gpu_layers=-1, n_ctx=4096,
)
output = model.create_chat_completion(
    messages=[{"role": "user", "content": "Hello!"}]
)

MLX Usage

pip install mlx-lm
mlx_lm.generate --model efops/marziel-8b-custom-MLX --prompt "Hello!"

OS API

GET  /os/status    — Kernel status
GET  /os/memory    — Memory tiers
GET  /os/ps        — Process list
GET  /os/top       — Resource monitor
POST /os/recall    — Memory recall
POST /os/remember  — Store memory
POST /os/schedule  — Schedule tasks
POST /os/kill/:pid — Kill process

Performance

52.9 tok/s on NVIDIA RTX A5000
75% KV cache memory savings
2.88-bit avg quantization

Model tree for efops/marziel-8b-custom

Base model

mistralai/Ministral-8B-Instruct-2410

Quantized

(69)

this model

efops
/

marziel-8b-custom