Community-built MiniMax H3 weights target 12GB–24GB GPUs with INT4 and NVFP4 variants

VoidAsuka · x · 2026-08-04

The post points to a community-compiled set of quantized and pruned MiniMax H3 weights in INT4, INT8, mixed, and NVFP4 formats.

According to the quoted text, the collection is aimed at users with 12GB–24GB VRAM GPUs, making the model more practical for consumer hardware and local experimentation.

Related event: Community Releases Quantized MiniMax H3 Weights(2 posts)→

Original post →

More from Infra

Infra channel →