---
title: DeepSeek-V4-Flash-EXTENSOR
canonical_url: "https://www.modelscope.ai/models/AMD/DeepSeek-V4-Flash-EXTENSOR"
md_url: "https://www.modelscope.ai/models/AMD/DeepSeek-V4-Flash-EXTENSOR.md"
repository: AMD/DeepSeek-V4-Flash-EXTENSOR
last_updated: 2026-08-07
license: mit
pipeline_tag: text-generation
tasks:
  - text-generation
base_model:
  - deepseek-ai/DeepSeek-V4-Flash-0731
base_model_relation: quantized
library_name:
  - gguf
  - pytorch
frameworks:
  - pytorch
downloads: 184
stars: 0
tags:
  - extensor
  - gguf
  - mixture-of-experts
  - quantized
  - deepseek-v4
  - mxfp4
---

# DeepSeek-V4-Flash-EXTENSOR

> DeepSeek-V4-Flash-EXTENSOR - An open-source model by AMD on ModelScope. DeepSeek-V4-Flash-0731 EXTENSOR

AMD/DeepSeek-V4-Flash-EXTENSOR is a text-generation model on ModelScope. licensed under mit. derived from deepseek-ai/DeepSeek-V4-Flash-0731.

- **Repository**: AMD/DeepSeek-V4-Flash-EXTENSOR
- **License**: mit
- **Tasks**: text-generation
- **Base model**: deepseek-ai/DeepSeek-V4-Flash-0731
- **Tags**: extensor, gguf, mixture-of-experts, quantized, deepseek-v4, mxfp4
- **Downloads**: 184
- **Stars**: 0
- **Last updated**: 2026-08-07

Source: https://www.modelscope.ai/models/AMD/DeepSeek-V4-Flash-EXTENSOR

---

# DeepSeek-V4-Flash-0731 EXTENSOR

An EXTENSOR runtime image derived from
[deepseek-ai/DeepSeek-V4-Flash-0731](https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash-0731).
It contains the target model only; the attached DSpark speculative module is not included.

## Artifact

- File: `DeepSeek-V4-Flash-EXTENSOR-MXFP4-Tile16-v2.extensor.gguf`
- Size: 155,848,011,776 bytes
- SHA-256: `9ce000f927b3693b508c523551453cd61b59363ffaef3f1949914d402c0674cd`
- Quantization: source-native MXFP4 Tile16

Requires EXTENSOR 2.0.0. This file is not compatible with llama.cpp.

## Source

`deepseek-ai/DeepSeek-V4-Flash-0731` at revision
`9e165c30e2704aec5d9d593cce3eebd58bbef1cb`.

## License

MIT License. See the upstream repository for usage and citation details.