---
title: Youtu-LLM-2B-4bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/Youtu-LLM-2B-4bit"
md_url: "https://www.modelscope.cn/models/mlx-community/Youtu-LLM-2B-4bit.md"
repository: mlx-community/Youtu-LLM-2B-4bit
last_updated: 2026-01-01
license: other
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - deepseek_v2
architectures:
  - YoutuForCausalLM
base_model:
  - tencent/Youtu-LLM-2B
base_model_relation: quantized
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 36
stars: 0
tags:
  - mlx
  - apple-silicon
  - tencent
  - youtu
  - reasoning
  - mla
  - 4-bit
---

# Youtu-LLM-2B-4bit

> Youtu-LLM-2B-4bit - mlx-community 在 ModelScope 开源的模型。Youtu-LLM-2B 4-bit MLX

mlx-community/Youtu-LLM-2B-4bit 是 ModelScope 魔搭社区上的text-generation模型，采用 other 许可，基于 tencent/Youtu-LLM-2B 构建。

- **Repository**: mlx-community/Youtu-LLM-2B-4bit
- **License**: other
- **Tasks**: text-generation
- **Base model**: tencent/Youtu-LLM-2B
- **Tags**: mlx, apple-silicon, tencent, youtu, reasoning, mla, 4-bit
- **Downloads**: 36
- **Stars**: 0
- **Last updated**: 2026-01-01

Source: https://www.modelscope.cn/models/mlx-community/Youtu-LLM-2B-4bit

---

# Youtu-LLM-2B 4-bit MLX

MLX-optimized 4-bit quantized version of [tencent/Youtu-LLM-2B](https://huggingface.co/tencent/Youtu-LLM-2B) for Apple Silicon.

## Quick Start

```bash
pip install mlx-lm

mlx_lm.generate \
  --model mlx-community/Youtu-LLM-2B-4bit \
  --prompt "Hello, what can you do?" \
  --max-tokens 100
```

## Model Details

- **Base Model:** tencent/Youtu-LLM-2B
- **Parameters:** 1.96B
- **Quantization:** 4-bit (4.5 bits/weight)
- **Context:** 128K tokens
- **Architecture:** Dense MLA (Multi-head Latent Attention)
- **Framework:** MLX (Apple Silicon optimized)

## Performance (M3 Ultra)

| Quant | Prompt | Generation | Memory |
|-------|--------|------------|--------|
| bf16 | 118 tok/s | 112 tok/s | 4.7GB |
| 4-bit | 202 tok/s | 205 tok/s | 1.3GB |

## Features

- **Reasoning Mode:** Uses `<think>` tags for Chain of Thought
- **128K Context:** Long document understanding
- **Agentic:** Strong on SWE-Bench, GAIA benchmarks
- **Edge-friendly:** Runs on any Apple Silicon Mac

## Benchmarks (vs Qwen3-4B)

| Benchmark | Youtu-LLM-2B | Qwen3-4B |
|-----------|--------------|----------|
| HumanEval | **95.9%** | 95.4% |
| SWE-Bench | **17.7%** | 5.7% |
| GAIA | **33.9%** | 25.5% |

## Other Quantizations

- [Full precision](https://huggingface.co/mlx-community/Youtu-LLM-2B) (4.4GB)
- [4-bit](https://huggingface.co/mlx-community/Youtu-LLM-2B-4bit) (1.2GB)

## Technical Note

Converted using deepseek_v2 architecture mapping (compatible MLA implementation).

## License

See [original model license](https://huggingface.co/tencent/Youtu-LLM-2B/blob/main/LICENSE.txt).