---
title: Dobby-Unhinged-Llama-3.3-70B-mlx-4Bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/Dobby-Unhinged-Llama-3.3-70B-mlx-4Bit"
md_url: "https://www.modelscope.cn/models/mlx-community/Dobby-Unhinged-Llama-3.3-70B-mlx-4Bit.md"
repository: mlx-community/Dobby-Unhinged-Llama-3.3-70B-mlx-4Bit
last_updated: 2025-09-15
license: llama3.3
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - llama
architectures:
  - LlamaForCausalLM
base_model:
  - SentientAGI/Dobby-Unhinged-Llama-3.3-70B
base_model_relation: quantized
parameters: 11.0B
tensor_type:
  - BF16
  - U32
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
inference_backends:
  - "deploy_task text/emb"
  - "lmdeploy 0.9.1"
  - "lmdeploy_turbomind 0.9.1"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 81
stars: 0
tags:
  - Llama-3.3
  - Instruct
  - "loyal AI"
  - fingerprint
  - finetune
  - chat
  - gpt4
  - "synthetic data"
  - roleplaying
  - unhinged
  - funny
  - opinionated
  - assistant
  - companion
  - friend
  - mlx
  - mlx-my-repo
---

# Dobby-Unhinged-Llama-3.3-70B-mlx-4Bit

> Dobby-Unhinged-Llama-3.3-70B-mlx-4Bit - mlx-community 在 ModelScope 开源的模型。mlx-community/Dobby-Unhinged-Llama-3.3-70B-mlx-4Bit

mlx-community/Dobby-Unhinged-Llama-3.3-70B-mlx-4Bit 是 ModelScope 魔搭社区上的 11.0B 参数text-generation模型，采用 llama3.3 许可，基于 SentientAGI/Dobby-Unhinged-Llama-3.3-70B 构建，可用 deploy_task text/emb、lmdeploy 0.9.1、lmdeploy_turbomind 0.9.1 部署。

- **Repository**: mlx-community/Dobby-Unhinged-Llama-3.3-70B-mlx-4Bit
- **License**: llama3.3
- **Tasks**: text-generation
- **Parameters**: 11.0B
- **Base model**: SentientAGI/Dobby-Unhinged-Llama-3.3-70B
- **Inference backends**: deploy_task text/emb, lmdeploy 0.9.1, lmdeploy_turbomind 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Tags**: Llama-3.3, Instruct, loyal AI, fingerprint, finetune, chat, gpt4, synthetic data, roleplaying, unhinged, funny, opinionated, assistant, companion, friend, mlx, mlx-my-repo
- **Downloads**: 81
- **Stars**: 0
- **Last updated**: 2025-09-15

Source: https://www.modelscope.cn/models/mlx-community/Dobby-Unhinged-Llama-3.3-70B-mlx-4Bit

---

# mlx-community/Dobby-Unhinged-Llama-3.3-70B-mlx-4Bit

The Model [mlx-community/Dobby-Unhinged-Llama-3.3-70B-mlx-4Bit](https://huggingface.co/mlx-community/Dobby-Unhinged-Llama-3.3-70B-mlx-4Bit) was converted to MLX format from [SentientAGI/Dobby-Unhinged-Llama-3.3-70B](https://huggingface.co/SentientAGI/Dobby-Unhinged-Llama-3.3-70B) 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/Dobby-Unhinged-Llama-3.3-70B-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)
```