QDNASales and integration of LLM inference and training platforms, on-premises or hybrid

How much memory does MiniMax M3 need in FP16?

MiniMax M3 has 428 billion parameters. The FP16 format decides how much memory is needed to load them.

Short answer. In FP16, the weights of MiniMax M3 take about 984 GB including the runtime margin. 4 of the 8 platforms in the catalogue have enough memory.

How is this footprint calculated?

MiniMax M3 totals 428 billion parameters. The FP16 format takes 2.0 byte per parameter. The product gives the weights, to which a 15% runtime margin is added for activations and buffers. The attention cache is not included: it grows with context and concurrency.

What does the format change?

FP16 brings full precision, the quality reference.

FormatWeights in memory Compatible platforms
FP16984 GB4
FP8492 GB7
NVFP4246 GB7
Q4246 GB7

Which platforms qualify?

See the MiniMax M3 fact sheet.

How much memory for MiniMax M3 in FP16?

About 984 GB for the weights, excluding the attention cache.

Which format should I choose for MiniMax M3?

FP16 brings full precision, the quality reference. The most precise format that fits the target machine remains the best choice.

Method

Parameter counts and memory figures come from the site fact sheets. Memory footprints are calculated, not measured: a reading on real hardware may differ depending on the engine and the exact weight format. Prices are indicative and not contractual.