Hacker News Reader

Comment by terhechte | Hacker News Reader

The weights have yet to be released. The previous MiniMax M3 had (I think) ~428B parameters. Since this one is called Flash and they advertise it as inference being 3 times faster, there's the possibility that this will be a ~150B size model which would (quantized) run on DGX Spark or 128GB Macs or the new AMD AI systems.

View on HN

The FAQ on their website says Minimax 3.1 flash is 428B total, 23B active

Which is roughly similar to deepseek 4.1 flash.

I find it interesting that we’re calling these “flash” models now, even though they aren’t “small or light” and in many cases aren’t particularly that fast.

I suppose it’s more so that the standard for “regular models” is becoming 1T+

https://agent.minimax.io/tools/m3-1-flash-preview

Flash probably means single expert fits into some cost efficient GPU memory, and non flash models require more complex and cost expensive architectures.

Agreed. 23b active parameters isn't flash in my book.

At 428B it can still fit on 2x 128GB machines at 4bpw, which is nice.

I think flash usually means MoE, not dense

Not really. “Flash” generally means fast or cost-efficient, not specifically MoE (Mixture of Experts).

- DeepSeek V4 Flash: 284B / 13B active MoE

- DeepSeek V4 Pro: 1.6T / 49B active MoE

- DeepSeek V4.1 Flash: 552B / 8B input, 16B output MoE

Every frontier model is MoE these days! Flash or otherwise. Sparsity just gets you more bang for your buck.

Reply on news.ycombinator.com