Kijai/MiniMax-H3-experimental

Hugging Face Models Trending Models

Summary

Kijai's MiniMax-H3-experimental is a work-in-progress model featuring w4a8 quantization and int8_convrot VAE support for ComfyUI, released for testing purposes.

Tags: region:us
Original Article
View Cached Full Text

Cached at: 08/08/26, 01:48 AM

Kijai/MiniMax-H3-experimental · Hugging Face

Source: https://huggingface.co/Kijai/MiniMax-H3-experimental **YAML Metadata Warning:**empty or missing yaml metadata in repo card

Check out thedocumentationfor more information.

w4a8 is work in progress, for testing only, further info here:

https://github.com/Comfy-Org/comfy-kitchen/pull/90

int8_convrot VAE currently needs this PR:https://github.com/Comfy-Org/ComfyUI/pull/15334

Downloads last month-

Downloads are not tracked for this model.

How to track

Inference ProvidersNEW

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

Similar Articles

Kijai/MiniMax-H3_comfy

Hugging Face Models Trending

A Hugging Face repository hosting MiniMax-H3 models converted for ComfyUI usage, along with a Lightx2v distill LoRA for faster inference.

realrebelai/MiniMax-H3_GGUFs

Hugging Face Models Trending

Hugging Face repository providing GGUF quantizations of MiniMax-H3 models for use with ComfyUI, including directory structure and links to required VAEs.

Comfy-Org/MiniMax-H3

Hugging Face Models Trending

Comfy-Org repackaged MiniMax-H3 model files for ComfyUI, including diffusion models, text encoders, and VAEs, with workflow templates for text-to-video, image-to-video, and reference-to-video generation.

sakamakismile/Qwen3-VL-32B-Heretic-MiniMax-H3-NVFP4

Hugging Face Models Trending

Release of an NVFP4-quantized uncensored MiniMax-H3 text encoder (Qwen3-VL-32B Heretic) that fits on a single 16GB GPU and serves as a drop-in replacement in ComfyUI workflows.