---
title: GalrionSoftworks_MagnusIntellectus-12B-v1
canonical_url: "https://www.modelscope.cn/models/mlx-community/GalrionSoftworks_MagnusIntellectus-12B-v1"
md_url: "https://www.modelscope.cn/models/mlx-community/GalrionSoftworks_MagnusIntellectus-12B-v1.md"
repository: mlx-community/GalrionSoftworks_MagnusIntellectus-12B-v1
last_updated: 2024-12-19
license: apache-2.0
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - mistral
architectures:
  - MistralForCausalLM
parameters: 3.4B
tensor_type:
  - U32
  - F16
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
inference_backends:
  - "deploy_task text/emb"
  - "lmdeploy 0.9.1"
  - "lmdeploy_turbomind 0.9.1"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 1010
stars: 0
tags:
  - merge
  - mergekit
  - lazymergekit
  - UsernameJustAnother/Nemo-12B-Marlin-v5
  - anthracite-org/magnum-12b-v2
  - mlx
---

# GalrionSoftworks_MagnusIntellectus-12B-v1

> GalrionSoftworks_MagnusIntellectus-12B-v1 - mlx-community 在 ModelScope 开源的模型。mlx-community/GalrionSoftworksMagnusIntellectus-12B-v1

mlx-community/GalrionSoftworks_MagnusIntellectus-12B-v1 是 ModelScope 魔搭社区上的 3.4B 参数text-generation模型，采用 apache-2.0 许可，可用 deploy_task text/emb、lmdeploy 0.9.1、lmdeploy_turbomind 0.9.1 部署。

- **Repository**: mlx-community/GalrionSoftworks_MagnusIntellectus-12B-v1
- **License**: apache-2.0
- **Tasks**: text-generation
- **Parameters**: 3.4B
- **Inference backends**: deploy_task text/emb, lmdeploy 0.9.1, lmdeploy_turbomind 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Tags**: merge, mergekit, lazymergekit, UsernameJustAnother/Nemo-12B-Marlin-v5, anthracite-org/magnum-12b-v2, mlx
- **Downloads**: 1010
- **Stars**: 0
- **Last updated**: 2024-12-19

Source: https://www.modelscope.cn/models/mlx-community/GalrionSoftworks_MagnusIntellectus-12B-v1

---

# mlx-community/GalrionSoftworks_MagnusIntellectus-12B-v1

The Model [mlx-community/GalrionSoftworks_MagnusIntellectus-12B-v1](https://huggingface.co/mlx-community/GalrionSoftworks_MagnusIntellectus-12B-v1) was converted to MLX format from [GalrionSoftworks/MagnusIntellectus-12B-v1](https://huggingface.co/GalrionSoftworks/MagnusIntellectus-12B-v1) using mlx-lm version **0.19.0**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/GalrionSoftworks_MagnusIntellectus-12B-v1")

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)
```