minimax-m3.1IMAGE

Skepticism that M3.1 Flash is a rebranded M3 with sparsified attention and quantization

A user suspects M3.1 Flash is just M3 rebranded, with attention sparsified in three more layers, quantization and DSpark added on top.

Teortaxes▶️ (DeepSeek 推特🐋铁粉 2023 – ∞)

@teortaxesTexArchived 5 days agoOriginally posted 2026.10.23

Skepticism that M3.1 Flash is a rebranded M3 with sparsified attention and quantization (image 1 of 2)

Skepticism that M3.1 Flash is a rebranded M3 with sparsified attention and quantization (image 2 of 2)

Teortaxes▶️ (DeepSeek 推特🐋铁粉 2023 – ∞) @teortaxesTexOriginally posted 2026.10.23

Open original on X

Bro they actually rebranded M3 as M3.1 Flash, just sparsified the attn in 3 more layers, quantized it and added DSpark on top I guess it's fair in a marketing sense, M3 is on the scale of today's Flash models, but… I didn't believe this

This post quotes another post: “MiniMax M3.1 Flash open weights: 428B total, 23B activated”

x.com/teortaxestex/status/2113447334021644595Archived 2026.10.23 12:09