---
base_model: FINAL-Bench/Darwin-4B-Genesis
language:
- ko
- en
- zh
- ja
- de
- fr
- es
license: apache-2.0
pipeline_tag: text-generation
library_name: transformers
tags:
- merge
- evolutionary-merge
- darwin
- darwin-v6
- model-mri
- cross-architecture
- ffn-crossbreed
- cma-es
- hybrid-vigor
- transformer-mamba
- reasoning
- gemma4
- qwen3.5
- gated-deltanet
- korean
- multilingual
- gpqa
- open-source
- world-first
- mlx
- mlx-my-repo
model-index:
- name: Darwin-4B-Genesis
  results:
  - task:
      type: text-generation
      name: Korean Cultural Understanding
    dataset:
      name: CLIcK
      type: EunsuKim/CLIcK
    metrics:
    - type: accuracy
      value: 92.0
      name: Accuracy
      verified: false
  - task:
      type: text-generation
      name: Multi-Step Reasoning
    dataset:
      name: MuSR
      type: TAUR-Lab/MuSR
    metrics:
    - type: accuracy
      value: 70.0
      name: Accuracy
      verified: false
---

# tomasmcm/Darwin-4B-Genesis-mlx-4Bit

The Model [tomasmcm/Darwin-4B-Genesis-mlx-4Bit](https://huggingface.co/tomasmcm/Darwin-4B-Genesis-mlx-4Bit) was converted to MLX format from [FINAL-Bench/Darwin-4B-Genesis](https://huggingface.co/FINAL-Bench/Darwin-4B-Genesis) using mlx-lm version **0.31.2**.

## Use with mlx

```bash
pip install mlx-lm
```

```python
from mlx_lm import load, generate

model, tokenizer = load("tomasmcm/Darwin-4B-Genesis-mlx-4Bit")

prompt="hello"

if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)
```