README.md

---
library_name: mlx
language:
- en
- fr
- de
- es
- pt
- it
- ja
- ko
- ru
- zh
- ar
- fa
- id
- ms
- ne
- pl
- ro
- sr
- sv
- tr
- uk
- vi
- hi
- bn
license: apache-2.0
tags:
- all use cases
- creative
- creative writing
- all genres
- tool calls
- tool use
- llama 3.1
- llama-3
- llama3
- llama-3.1
- problem solving
- deep thinking
- reasoning
- deep reasoning
- story
- writing
- fiction
- roleplaying
- bfloat16
- role play
- sillytavern
- backyard
- context 128k
- mergekit
- merge
- moe
- mixture of experts
- mlx
pipeline_tag: text-generation
base_model: DavidAU/Llama3.1-MOE-4X8B-Gated-IQ-Multi-Tier-Deep-Reasoning-32B
---

# Llama3.1-MOE-4X8B-Gated-IQ-Multi-Tier-Deep-Reasoning-32B-q8-mlx

This model [Llama3.1-MOE-4X8B-Gated-IQ-Multi-Tier-Deep-Reasoning-32B-q8-mlx](https://huggingface.co/Llama3.1-MOE-4X8B-Gated-IQ-Multi-Tier-Deep-Reasoning-32B-q8-mlx) was
converted to MLX format from [DavidAU/Llama3.1-MOE-4X8B-Gated-IQ-Multi-Tier-Deep-Reasoning-32B](https://huggingface.co/DavidAU/Llama3.1-MOE-4X8B-Gated-IQ-Multi-Tier-Deep-Reasoning-32B)
using mlx-lm version **0.26.0**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("Llama3.1-MOE-4X8B-Gated-IQ-Multi-Tier-Deep-Reasoning-32B-q8-mlx")

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)
```