---
title: Llama-3_3-Nemotron-Super-49B-v1_5-mlx-4Bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/Llama-3_3-Nemotron-Super-49B-v1_5-mlx-4Bit"
md_url: "https://www.modelscope.cn/models/mlx-community/Llama-3_3-Nemotron-Super-49B-v1_5-mlx-4Bit.md"
repository: mlx-community/Llama-3_3-Nemotron-Super-49B-v1_5-mlx-4Bit
last_updated: 2025-09-15
license: other
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - nemotron-nas
architectures:
  - DeciLMForCausalLM
base_model:
  - unsloth/Llama-3_3-Nemotron-Super-49B-v1_5
base_model_relation: quantized
parameters: 7.8B
tensor_type:
  - BF16
  - U32
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
inference_backends:
  - "deploy_task text/emb"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 83
stars: 0
tags:
  - nvidia
  - "unsloth - llama-3 - pytorch"
  - mlx
  - mlx-my-repo
---

# Llama-3_3-Nemotron-Super-49B-v1_5-mlx-4Bit

> Llama-3_3-Nemotron-Super-49B-v1_5-mlx-4Bit - mlx-community 在 ModelScope 开源的模型。mlx-community/Llama-33-Nemotron-Super-49B-v15-mlx-4Bit

mlx-community/Llama-3_3-Nemotron-Super-49B-v1_5-mlx-4Bit 是 ModelScope 魔搭社区上的 7.8B 参数text-generation模型，采用 other 许可，基于 unsloth/Llama-3_3-Nemotron-Super-49B-v1_5 构建，可用 deploy_task text/emb、sglang 0.5.2、vllm 0.9.2 部署。

- **Repository**: mlx-community/Llama-3_3-Nemotron-Super-49B-v1_5-mlx-4Bit
- **License**: other
- **Tasks**: text-generation
- **Parameters**: 7.8B
- **Base model**: unsloth/Llama-3_3-Nemotron-Super-49B-v1_5
- **Inference backends**: deploy_task text/emb, sglang 0.5.2, vllm 0.9.2
- **Tags**: nvidia, unsloth - llama-3 - pytorch, mlx, mlx-my-repo
- **Downloads**: 83
- **Stars**: 0
- **Last updated**: 2025-09-15

Source: https://www.modelscope.cn/models/mlx-community/Llama-3_3-Nemotron-Super-49B-v1_5-mlx-4Bit

---

# mlx-community/Llama-3_3-Nemotron-Super-49B-v1_5-mlx-4Bit

The Model [mlx-community/Llama-3_3-Nemotron-Super-49B-v1_5-mlx-4Bit](https://huggingface.co/mlx-community/Llama-3_3-Nemotron-Super-49B-v1_5-mlx-4Bit) was converted to MLX format from [unsloth/Llama-3_3-Nemotron-Super-49B-v1_5](https://huggingface.co/unsloth/Llama-3_3-Nemotron-Super-49B-v1_5) using mlx-lm version **0.26.4**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Llama-3_3-Nemotron-Super-49B-v1_5-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)
```