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.

▲

penagwin 4 hours ago | parent | next [-]

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

	▲	andriy_koval 3 hours ago \| parent [-]
		Flash probably means single expert fits into some cost efficient GPU memory, and non flash models require more complex and cost expensive architectures.

▲

PcChip 5 hours ago | parent | prev [-]

I think flash usually means MoE, not dense

	▲	jephs 5 hours ago \| parent \| next [-]
		Every frontier model is MoE these days! Flash or otherwise. Sparsity just gets you more bang for your buck.
	▲	terhechte 5 hours ago \| parent \| prev [-]
		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