---
title: DeepSeek-V4-Flash-0731-MLX-Q3i
canonical_url: "https://www.modelscope.ai/models/inferencerlabs/DeepSeek-V4-Flash-0731-MLX-Q3i"
md_url: "https://www.modelscope.ai/models/inferencerlabs/DeepSeek-V4-Flash-0731-MLX-Q3i.md"
repository: inferencerlabs/DeepSeek-V4-Flash-0731-MLX-Q3i
last_updated: 2026-09-02
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - deepseek_v4
architectures:
  - DeepseekV4ForCausalLM
base_model:
  - deepseek-ai/DeepSeek-V4-Flash-0731
base_model_relation: quantized
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
downloads: 75
stars: 0
tags:
  - quantized
  - mlx
---

# DeepSeek-V4-Flash-0731-MLX-Q3i

> DeepSeek-V4-Flash-0731-MLX-Q3i - An open-source model by inferencerlabs on ModelScope. See DeepSeek-V4-Flash-0731 MLX in action - demonstration videos Tested with an M3 Ultra 512 GiB using Inferencer app Text inference: 39.7 tokens/s @ 500 tokens 104.6 GiB

inferencerlabs/DeepSeek-V4-Flash-0731-MLX-Q3i is a text-generation model on ModelScope. derived from deepseek-ai/DeepSeek-V4-Flash-0731.

- **Repository**: inferencerlabs/DeepSeek-V4-Flash-0731-MLX-Q3i
- **Tasks**: text-generation
- **Base model**: deepseek-ai/DeepSeek-V4-Flash-0731
- **Tags**: quantized, mlx
- **Downloads**: 75
- **Stars**: 0
- **Last updated**: 2026-09-02

Source: https://www.modelscope.ai/models/inferencerlabs/DeepSeek-V4-Flash-0731-MLX-Q3i

---

**See DeepSeek-V4-Flash-0731 MLX in action - [demonstration videos](https://youtube.com/xcreate)**
   
#### Tested with an M3 Ultra 512 GiB using [Inferencer app](https://inferencer.com)
- Text inference: ~39.7 tokens/s @ 500 tokens ~104.6 GiB

<p style="margin-bottom:0px;">
This build uses the data-agnostic INF method to compresses the model to operate within the memory constraints of a 128 GiB RAM system while maintaining response coherence.

Consider increasing the available RAM for inferencing with:
- ```sudo sysctl iogpu.wired_limit_mb=118000```
</p>

![Screenshot](https://cdn-uploads.huggingface.co/production/uploads/688479d616f1ec82fa645019/wOCIKD8XeGCmFKM4ZEmDE.jpeg)

##### Quantized with a modified version of [MLX](https://github.com/ml-explore/mlx)
##### For more details see our [demonstration videos](https://youtube.com/xcreate) or visit [DeepSeek-V4-0731](https://huggingface.co/deepseek-ai/DeepSeek-V4-0731).

## 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.