Event ·Multi-source

MiniMax M3.1 Flash 与 Unsloth 合作,428B 模型量化至 143.9GB

MiniMax 宣布与 Unsloth 社区合作,为 M3.1 Flash 提供 Dynamic GGUF 量化版本。这个 428B 参数的 MoE 模型被压缩到 143.9GB 的 2-bit 体积,Unsloth 评估显示在七个领域中保持 91.5% 的 top-1 token 一致率。用户可通过 Unsloth Desktop 和 llama.cpp 自部署,还能用 OpenAI 兼容 API 接入现有应用。Unsloth 在 GitHub 有 78K+ stars,Hugging Face 下载量超过 5 亿次。

Current read

MiniMax 的 428B 大模型被 Unsloth 压到 143.9GB 还能保持 91.5% 的输出一致率,想本地跑开源模型的朋友可以试试。

11 sources64° AI heatLast updated 2026/10/26 20:25:11

Evidence

11 sources
Related source 1TestingCatalog
View source
Related source 2Artificial Analysis
View source
Related source 3Bindu Reddy
View source
Related source 4The Rundown AI
View source
Related source 7kimmonismus
View source
Related source 8Nathan Lambert
View source
Related source 9OpenAI Blog
View source
Related source 10@koltregaskes
View source

Conflict check

Dedup data only shows that these sources discuss the same event, not that they agree. There is no structured supporting or refuting evidence yet, so no conflict is inferred automatically.

MiniMax M3.1 Flash 与 Unsloth 合作,428B 模型量化至 143.9GB · 事件专题 | AITOP