# Atomic 发布 DeepSeek V4 Flash 14 种量化版本

- 来源：🚨 AI News | TestingCatalog (@testingcatalog)
- 发布时间：2026-08-04 05:30
- AIHOT 分数：48
- AIHOT 链接：https://aihot.virxact.com/items/cmsdr4jpp00qoromah44h6skt
- 原文链接：https://x.com/testingcatalog/status/2084391415103058394

## AI 摘要

Atomic 在 Hugging Face 发布 DeepSeek V4 Flash 0731 的 14 种量化版本，覆盖无损 BF16 到 1-bit。该模型为 284B 参数 MoE，采用量化感知训练，官方检查点以 MXFP4 存储路由专家。其中 AD-IQ2_M 最适合 128GB 硬件，token 匹配率达 83.6%。

## 正文

Atomic released 14 quants of "DeepSeek V4 Flash 0731" on Huggingface with the best "quality vs size" performance.

> DeepSeek-V4-Flash is a 284B parameter mixture-of-experts model. It is quantization-aware-trained； the official checkpoint already stores its routed experts in MXFP4 and everything else in FP8 or BF16.

The AD-IQ2_M version is the best for testing on 128GB hardware！

### 引用推文

> atomic.chat：Run DeepSeek V4 Flash 0731 locally 🐳 We released 14 quants on Hugging Face, from lossless BF16 to 1-bit AD-IQ2_M is the best fit for 128GB hardware. It matches...