Instructions to use Apfelkringel/Qwen3.5-9B-Bioinformatik with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Apfelkringel/Qwen3.5-9B-Bioinformatik 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("Apfelkringel/Qwen3.5-9B-Bioinformatik")

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)

Notebooks
Google Colab
Kaggle
Local Apps
LM Studio

Pi new

How to use Apfelkringel/Qwen3.5-9B-Bioinformatik with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "Apfelkringel/Qwen3.5-9B-Bioinformatik"

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": "Apfelkringel/Qwen3.5-9B-Bioinformatik"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Apfelkringel/Qwen3.5-9B-Bioinformatik 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 "Apfelkringel/Qwen3.5-9B-Bioinformatik"

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 Apfelkringel/Qwen3.5-9B-Bioinformatik

Run Hermes

hermes

MLX LM

How to use Apfelkringel/Qwen3.5-9B-Bioinformatik with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "Apfelkringel/Qwen3.5-9B-Bioinformatik"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "Apfelkringel/Qwen3.5-9B-Bioinformatik"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "Apfelkringel/Qwen3.5-9B-Bioinformatik",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Qwen3.5-9B-Bioinformatik (Deutsch)

Ein feingetuntes Qwen3.5 9B Modell für Bioinformatik-Fragen auf Deutsch mit Chain-of-Thought Reasoning.

Model Details

Base Model: Qwen3.5-9B (Claude Opus 4.6 Reasoning Distilled)
Parameters: 9 Billion (9B)
Training: LoRA Fine-Tuning mit 3000 Iterationen
Dataset: Bioinformatik QA (yashm/bioinformatics-qa-dataset)
Format: MLX (Apple Silicon optimiert)
Quantization: 4-bit
Precision: BF16

Hardware Requirements

Apple Silicon Mac (M1/M2/M3/M4)
Minimum 16GB RAM (empfohlen: 32GB)
macOS 14.0+

Features

Deutsche Bioinformatik-Antworten
Chain-of-Thought Reasoning
Schnelle Inference auf Apple Silicon
Themen: BLAST, Sequenzierung, FASTA, ORFs, Phylogenetik, Microarrays, Smith-Waterman, E-Values

Usage

from mlx_lm import load, generate

model, tokenizer = load("Apfelkringel/Qwen3.5-9B-Bioinformatik")

messages = [{"role": "user", "content": "Was ist ein BLAST-Algorithmus?"}]
prompt = tokenizer.apply_chat_template(messages, add_generation_prompt=True)
response = generate(model, tokenizer, prompt=prompt, max_tokens=400)
print(response)

Benchmark Results

Metric	Value
Antwort-Länge	~140 Wörter
Geschwindigkeit	~15s (Apple Silicon)
Deutsch	✓
Chain-of-Thought	✓
Parameters	9B

Fine-Tuning Configuration

LoRA Rank: 16
Learning Rate: 3e-5
Iterations: 3000
Batch Size: 1
Trainable Parameters: 0.121% (~10.8M params)

Limitations

Optimiert für Bioinformatik-Themen
9B Parameter Modell
Französisch und Englisch werden auch akzeptiert

Citation

@misc{Qwen35-9B-Bioinformatik,
  author = {Apfelkringel},
  title = {Qwen3.5-9B-Bioinformatik: German Fine-tuned Bioinformatik Model},
  year = {2025},
  publisher = {HuggingFace},
  url = {https://huggingface.co/Apfelkringel/Qwen3.5-9B-Bioinformatik}
}

Trained with ❤️ using mlx-lm on Apple Silicon M-Series