MiniMax-H3-fp8

FP8 (float8_e4m3fn) quantized version of MiniMax H3, for use in ComfyUI.

Details Format: weight-only scaled FP8 (float8_e4m3fn)

Not official: this is an unofficial conversion.

Usage

Drop the .safetensors file into ComfyUI/models/diffusion_models/ and load it like the standard MiniMax H3 checkpoint.

Base Model

Original weights: MiniMaxAI/MiniMax-H3

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for dimitarx/MiniMax-H3-fp8

Base model

Finetuned

(28)

this model