---
title: Intellect-2-TQ2-0
canonical_url: "https://www.modelscope.cn/models/sleeping-ai/Intellect-2-TQ2-0"
md_url: "https://www.modelscope.cn/models/sleeping-ai/Intellect-2-TQ2-0.md"
repository: sleeping-ai/Intellect-2-TQ2-0
last_updated: 2025-07-07
license: mit
pipeline_tag: text-generation
tasks:
  - text-generation
base_model:
  - PrimeIntellect/INTELLECT-2
base_model_relation: quantized
library_name:
  - gguf
  - pytorch
frameworks:
  - pytorch
language:
  - en
downloads: 204
stars: 0
tags:
  - gguf
---

# Intellect-2-TQ2-0

> Intellect-2-TQ2-0 - sleeping-ai 在 ModelScope 开源的模型。Outlook We have quantised the model in 2-bit to make it inferenceable in low-end GPU cards at scale. It was achieved thanks to llama.cpp library.

sleeping-ai/Intellect-2-TQ2-0 是 ModelScope 魔搭社区上的text-generation模型，采用 mit 许可，基于 PrimeIntellect/INTELLECT-2 构建。

- **Repository**: sleeping-ai/Intellect-2-TQ2-0
- **License**: mit
- **Tasks**: text-generation
- **Base model**: PrimeIntellect/INTELLECT-2
- **Tags**: gguf
- **Downloads**: 204
- **Stars**: 0
- **Last updated**: 2025-07-07

Source: https://www.modelscope.cn/models/sleeping-ai/Intellect-2-TQ2-0

---

### Outlook
We have quantised the model in 2-bit to make it inferenceable in low-end GPU cards at scale. It was achieved thanks to llama.cpp library.