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

Serving MiniMax M3 with Unsloth

MiniMax M3 has 428 billion parameters. Unsloth targets fine-tuning and quantisation. This page gives the memory required and the platforms that qualify.

Short answer. Unsloth serves MiniMax M3 as soon as the machine offers at least 246 GB of memory, the weight footprint in NVFP4. 7 of the 8 platforms in the catalogue meet that bar.

What is the minimum memory?

MiniMax M3 totals 428 billion parameters. In NVFP4 its weights take about 246 GB including the runtime margin. In FP8 the footprint doubles, to about 492 GB. The attention cache sits on top and depends on the context served.

What is Unsloth for?

Unsloth targets fine-tuning and quantisation. See the Unsloth and MiniMax M3 fact sheets.

On which platforms?

How much memory for MiniMax M3 with Unsloth?

About 246 GB in NVFP4 for the weights, excluding the attention cache.

Does Unsloth suit MiniMax M3?

Unsloth serves MiniMax M3 as soon as the machine offers at least 246 GB of memory, the weight footprint in NVFP4. 7 of the 8 platforms in the catalogue meet that bar.

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.