MiniMax-Text models

1 MiniMax-Text model from MiniMax on Hugging Face, from 456.1B to 456.1B parameters, published by MiniMax in BF16, with a 10000K-token context. The smallest official model, MiniMax-Text-01-hf, needs about 1019 GB of VRAM at its published precision; the cheapest live fit is AMD MI300X at $15.77/hr.

Part of the MiniMax series · Next generation: MiniMax M2

Pick a size

One row per official MiniMax-Text size: the VRAM it needs at each precision, the cheapest GPU that holds it today, and the KV cache for a 32K-token context.

ModelParametersNative VRAMFP8 VRAMINT4 VRAMLive GPU fit (native)Est. $/hrKV cache at 32K
MiniMax-Text-01-hf456.1B1019 GB510 GB255 GBAMD MI300X × 6$15.77/hr1.3 GB

VRAM is weights times a flat 1.2 overhead; the KV cache is a separate per-model figure at 16-bit, shown where the architecture is published. See the methodology.

Official models (1)

ModelParametersPublished asVRAM neededLive GPU fitEst. $/hr
MiniMax-Text-01-hf456.1BBF161019 GBAMD MI300X × 6$15.77/hr

VRAM is for the precision the model is published in: the weights times a flat 1.2 overhead, with the KV cache not included. See the methodology. The fit shown is the lowest-priced single GPU type that holds the model at that precision, or the lowest-priced multi-GPU set (up to 8) when none does.

More from MiniMax

Start ComfyUI on a rented GPU.

© 2026 Aquanode. All rights reserved.

All trademarks, logos and brand names are the property of their respective owners.