---
title: DeepSeek-V4-Flash-162B-GGUF
canonical_url: "https://www.modelscope.cn/models/0xSero/DeepSeek-V4-Flash-162B-GGUF"
md_url: "https://www.modelscope.cn/models/0xSero/DeepSeek-V4-Flash-162B-GGUF.md"
repository: 0xSero/DeepSeek-V4-Flash-162B-GGUF
last_updated: 2026-07-18
license: mit
pipeline_tag: text-generation
tasks:
  - text-generation
base_model:
  - 0xSero/DeepSeek-V4-Flash-162B
base_model_relation: quantized
library_name:
  - gguf
  - pytorch
frameworks:
  - pytorch
downloads: 297
stars: 1
tags:
  - deepseek
  - deepseek-v4
  - dgx-spark
  - ds4
  - dwarfstar
  - gguf
  - reap
---

# DeepSeek-V4-Flash-162B-GGUF

> DeepSeek-V4-Flash-162B-GGUF - 0xSero 在 ModelScope 开源的模型。[!TIP] Support this work → · X · GitHub · REAP paper · Cerebras REAP

0xSero/DeepSeek-V4-Flash-162B-GGUF 是 ModelScope 魔搭社区上的text-generation模型，采用 mit 许可，基于 0xSero/DeepSeek-V4-Flash-162B 构建。

- **Repository**: 0xSero/DeepSeek-V4-Flash-162B-GGUF
- **License**: mit
- **Tasks**: text-generation
- **Base model**: 0xSero/DeepSeek-V4-Flash-162B
- **Tags**: deepseek, deepseek-v4, dgx-spark, ds4, dwarfstar, gguf, reap
- **Downloads**: 297
- **Stars**: 1
- **Last updated**: 2026-07-18

Source: https://www.modelscope.cn/models/0xSero/DeepSeek-V4-Flash-162B-GGUF

---

> [!TIP]
> **[Support this work →](https://donate.sybilsolutions.ai)** · [X](https://x.com/0xsero) · [GitHub](https://github.com/0xsero) · [REAP paper](https://arxiv.org/abs/2510.13999) · [Cerebras REAP](https://huggingface.co/collections/cerebras/cerebras-reap)

# DeepSeek-V4-Flash-162B-GGUF

GGUF quantization of [0xSero/DeepSeek-V4-Flash-162B](https://huggingface.co/0xSero/DeepSeek-V4-Flash-162B).

## At a glance

| | |
|---|---|
| Base model | [0xSero/DeepSeek-V4-Flash-162B](https://huggingface.co/0xSero/DeepSeek-V4-Flash-162B) |
| Format | GGUF |
| Total params | **162B** |
| Active / token | — |
| Experts / layer | — |
| Layers | — |
| Hidden size | — |
| Context | — |
| On-disk size | 149 GB |

## Which variant should I pick?

| Variant | Format | Link |
|---|---|---|
| `DeepSeek-V4-Flash-162B` | BF16 | [link](https://huggingface.co/0xSero/DeepSeek-V4-Flash-162B) |
| `DeepSeek-V4-Flash-162B-GGUF` **(this)** | GGUF | [link](https://huggingface.co/0xSero/DeepSeek-V4-Flash-162B-GGUF) |
| `DeepSeek-V4-Flash-180B` | BF16 | [link](https://huggingface.co/0xSero/DeepSeek-V4-Flash-180B) |
| `DeepSeek-V4-Flash-180B-GGUF` | GGUF | [link](https://huggingface.co/0xSero/DeepSeek-V4-Flash-180B-GGUF) |
| `DeepSeek-V4-Flash-213B` | BF16 | [link](https://huggingface.co/0xSero/DeepSeek-V4-Flash-213B) |

This repository contains DS4/DwarfStar GGUF conversions of `DeepSeek-V4-Flash-Spark-Mini`.

The GGUFs point back to the original Spark Hugging Face model:

- Original Spark model: https://huggingface.co/0xSero/DeepSeek-V4-Flash-162B
- Conversion source checkpoint: https://huggingface.co/0xSero/DeepSeek-V4-Flash-162B-codex-K144-REAP
- Runtime/converter repo: https://github.com/antirez/ds4
- Spark deployment repo: https://github.com/0xSero/deepseek-spark

## Files

| File | Size | SHA256 |
| --- | ---: | --- |
| `DeepSeek-V4-Flash-Spark-Mini-Q2-REAP-ds4.gguf` | 48.98 GiB | `e917278028d7a9e25dfc9d04bf5848375dad7573c5aeab1720d6a83714352406` |

## Quantization

- `Q2-REAP-ds4`: compact DS4 profile using `IQ2_XXS` routed gate/up experts, `Q2_K` routed down experts, and `Q8_0` shared/output/attention projections.

These are DS4/DwarfStar-specific GGUF files for DeepSeek-V4 Flash REAP checkpoints. They are not generic llama.cpp files unless your runtime supports the same DeepSeek-V4 Flash tensor layout and DS4 metadata.

## Validation

Validation summaries are uploaded in this repo under:

- `validation/20260528T160633Z/SUMMARY.md`
- `validation/20260528T160633Z/summary.json`

The Mini Q2 GGUF completed the DS4 context sweep through `200000` context on one DGX Spark:

| Context | Prefill tok/s | Decode tok/s | KV bytes |
| ---: | ---: | ---: | ---: |
| 2,048 | 348.19 | 12.75 | 52,184,460 |
| 4,096 | 358.51 | 13.50 | 80,373,132 |
| 8,192 | 352.29 | 13.32 | 136,750,476 |
| 16,384 | 348.25 | 13.24 | 249,505,164 |
| 32,768 | 322.07 | 12.40 | 475,014,540 |
| 65,536 | 287.26 | 11.49 | 926,033,292 |
| 131,072 | 241.57 | 9.81 | 1,828,070,796 |
| 200,000 | 194.24 | 9.17 | 2,776,775,308 |

API probes completed through at least the `131072` window before `spark-2822` became unreachable during the tail of the `200000` validation step:

| Context | Prompt tokens | TTFT seconds | Prefill tok/s | Decode tok/s | Marker visible |
| ---: | ---: | ---: | ---: | ---: | --- |
| 65,536 | 59,867 | 176.54 | 339.12 | 13.01 | true |
| 131,072 | 119,696 | 390.59 | 306.45 | 11.70 | true |

This repo publishes the validated Q2 long-context profile only.

## License & citation
License inherited from the base model.

```bibtex
@misc{lasby2025reap,
  title  = {REAP the Experts: Why Pruning Prevails for One-Shot MoE Compression},
  author = {Mike Lasby and Ivan Lazarevich and Nish Sinnadurai and Sean Lie and Yani Ioannou and Vithursan Thangarasa},
  year   = {2025}, eprint = {2510.13999}, archivePrefix = {arXiv}
}
```

## Sponsors
Made possible by **NVIDIA · TNG Technology · Lambda · Prime Intellect · Hot Aisle**.
