# Kimi K3 1-bit 量化：2.8T 模型缩至 590GB

- 来源：Rohan Paul (@rohanpaul_ai)
- 发布时间：2026-08-01 01:47
- AIHOT 分数：44
- AIHOT 链接：https://aihot.virxact.com/items/cms98yanv08kgro9k8pu54i64
- 原文链接：https://x.com/rohanpaul_ai/status/2083248175792726223

## AI 摘要

Atomic Chat 将 Kimi K3 量化为 1-bit，模型从 2.8T 参数压缩至 590GB（-62%），保留 78.7% 原始质量和完整 1M 上下文。

## 正文

Really cool. @atomic_chat_hq 's 1-bit Kimi K3 quant shrinks the 2.8T model to 590GB （-62%）

- The 1-bit model keeps 78.7% of the original quality and the full 1M context. model on Huggingface

- Moving to 2.1 bits raises the footprint to 769GB， but agreement jumps to 87.2%. Going all the way to 3.4 bits adds another 428GB for only 0.5 percentage points.

- In their HTML 3D physics test， all 4 models handled the drop physics， while only local K3 built the requested working winch.

- They ran it with on 4x B200 GPUs

### 引用推文

> atomic.chat：1-bit Kimi K3 performs at Opus 5 level on 3D physics! We ran our Atomic Chat quant of Kimi K3 locally on 4x B200 against three cloud models and gave them all th...