minimax-m3.1POST
MiniMax M3.1 Flash GGUF build coming to Project-Maya for local inference
A developer says a GGUF quant of M3.1 Flash is coming to Project-Maya and expects it to run faster than DeepSeek V4.1 Flash on an RTX 3090 given its smaller size.
AJ
@ItsmeAjayKVArchived 1 day agoOriginally posted 2026.10.27
AJ @ItsmeAjayKVOriginally posted 2026.10.27
Attention ! MiniMax-M3.1-Flash gguf for running in Project-Maya coming soon 👀 @PeasantSmith and @needmorevram are doing phenomenal job 🫡 Cannot wait to try it out, since it's smaller than deepseek-v4.1-flash it should be more faster on my RTX 3090 system
This post quotes another post: x.com/peasantsmith/status/2114855806860439754
x.com/itsmeajaykv/status/2114893183499038957Archived 2026.10.27 12:04