---
title: DeepSeek-V3.2-MLX-Q4
canonical_url: "https://www.modelscope.ai/models/inferencerlabs/DeepSeek-V3.2-MLX-Q4"
md_url: "https://www.modelscope.ai/models/inferencerlabs/DeepSeek-V3.2-MLX-Q4.md"
repository: inferencerlabs/DeepSeek-V3.2-MLX-Q4
last_updated: 2026-09-02
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - deepseek_v32
architectures:
  - DeepseekV32ForCausalLM
base_model:
  - deepseek-ai/DeepSeek-V3.2
base_model_relation: quantized
parameters: 111.6B
tensor_type:
  - U32
  - BF16
  - F32
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
downloads: 85
stars: 0
tags:
  - quantized
  - mlx
---

# DeepSeek-V3.2-MLX-Q4

> DeepSeek-V3.2-MLX-Q4 - An open-source model by inferencerlabs on ModelScope. See DeepSeek-V3.2 MLX in action - demonstration video

inferencerlabs/DeepSeek-V3.2-MLX-Q4 is a 111.6B-parameter text-generation model on ModelScope. derived from deepseek-ai/DeepSeek-V3.2.

- **Repository**: inferencerlabs/DeepSeek-V3.2-MLX-Q4
- **Tasks**: text-generation
- **Parameters**: 111.6B
- **Base model**: deepseek-ai/DeepSeek-V3.2
- **Tags**: quantized, mlx
- **Downloads**: 85
- **Stars**: 0
- **Last updated**: 2026-09-02

Source: https://www.modelscope.ai/models/inferencerlabs/DeepSeek-V3.2-MLX-Q4

---

**See DeepSeek-V3.2 MLX in action - [demonstration video](https://youtu.be/b6RgBIROK5o)**

*q4.8bit mixed quant typically achieves 1.14 perplexity in our testing*
| Quantization | Perplexity |
|:------------:|:----------:|
| **q2.5**     | 41.293     |
| **q3.5**     | 1.900      |
| **q4.5**     | 1.168      |
| **q4.8**     | 1.140      |
| **q5.5**     | 1.141      |
| **q6.5**     | 1.128      |
| **q8.5**     | 1.128      |

## Usage Notes
    
#### Tested by remotely connecting to a M3 Ultra 512GB RAM using [Inferencer app v1.7.3](https://inferencer.com)
* Expect ~18 tokens/s @ 1000 tokens
* Memory usage: ~382 GB

##### Quantized with a modified version of [MLX](https://github.com/ml-explore/mlx) 0.28
##### For more details see [demonstration video](https://youtu.be/b6RgBIROK5o) or visit [DeepSeek-V3.2](https://huggingface.co/deepseek-ai/DeepSeek-V3.2).

## Disclaimer

We are not the creator, originator, or owner of any model listed. Each model is created and provided by third parties. Models may not always be accurate or contextually appropriate. You are responsible for verifying the information before making important decisions. We are not liable for any damages, losses, or issues arising from its use, including data loss or inaccuracies in AI-generated content.