---
library_name: mlx
license: apache-2.0
pipeline_tag: text-generation
base_model: fastino/Fastino-Nemotron-3.5-Lightning-Healthcare
tags:
  - mlx
  - nemotron_h
  - 4-bit
---

# Fastino-Nemotron-3.5-Lightning-Healthcare-MLX-4bit

This model was converted to MLX format from [fastino/Fastino-Nemotron-3.5-Lightning-Healthcare](https://huggingface.co/fastino/Fastino-Nemotron-3.5-Lightning-Healthcare) using mlx-lm version **0.31.3**.

| Property | Value |
|----------|-------|
| Quantization | 4-bit affine |
| Group size | 64 |

## Use with mlx

```bash
pip install mlx-lm
mlx_lm.generate --model Fastino-Nemotron-3.5-Lightning-Healthcare-MLX-4bit --prompt "Hello"
```

```python
from mlx_lm import load, generate

model, tokenizer = load("Fastino-Nemotron-3.5-Lightning-Healthcare-MLX-4bit")
prompt = "Hello"
if tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(messages, add_generation_prompt=True)
response = generate(model, tokenizer, prompt=prompt, verbose=True)
```