AITOPAI热报
Models

MiniMax M3.1 Flash 的 GGUF 量化版本发布，可本地部署

@atomic_chat_hq@atomic_chat_hq
Post
View the post
Why we picked it

MiniMax 那个 428B 的 M3.1 Flash 出 GGUF 了，有 256GB 内存的机器可以下载 203.5GB 的 Q3_K_M 版本本地跑。

Atomic Chat 在 Hugging Face 上发布了 MiniMax M3.1 Flash（428B 参数）的 GGUF 量化模型，体积从 258GB 到 203.5GB 不等。官方推荐使用 203.5GB 的 Q3_K_M 量化版本，适合 256GB 内存的硬件运行。用户可在本地设备上部署该模型而无需依赖云端服务。

Image · @atomic_chat_hq
Original · @atomic_chat_hq

Run MiniMax M3.1 Flash locally 🐰

We released GGUFs of @MiniMax_AI's new 428B model on Hugging Face from 258GB down to 203.5GB

We recommend our 203.5GB Q3_K_M quant for 256GB hardware

GGUFs 👇 https://t.co/DBTR9IXvD0

#MiniMax#M3.1 Flash#GGUF#开源模型

Keep reading

Recent stories with the same tag or section
ModelsBuildersSelected11:25
MiniMax M3.1 Flash Runs in Production on vLLM

Production-grade serving of a MiniMax model through vLLM signals that the open-source inference stack can now carry commercial workloads with SLA guarantees. Teams evaluating cheaper open-weight serving options can look at Inferact's vLLM-based offering as a reference setup. Upstream contributions also mean the wider vLLM community inherits the reliability hardening that came out of this deployment.

#MiniMax#vLLM#open-source models#inference
官方账号vLLM@vllm_projectSource