Documentation Navigation

Models & pricing / Models / MiniMax-H3-experimental

MiniMax-H3-experimental Overview

This model's data has not been fully verified and benchmarks may be missing.

MiniMax-H3-experimental is a chat-reasoning AI model created by Kijai, featuring undisclosed parameters and a context window of unknown.

An experimental model using 4-bit weights and int8-convrot activations, with a VAE that speeds up decode times by ~1.5x, built by Comfy-Org.

Model Lineage & Specification

minimax-h3-experimental is Kijai's primary release in the current family.

DeveloperKijai
API Identifierminimax-h3-experimental
Parametersundisclosed
Context Windowunknown
LicenseUnknown

Comparable models

MiniMax-H3-experimental

An experimental model using 4-bit weights and int8-convrot activations, with a V...

API IDminimax-h3-experimental
Typeopen weights
Parameters
Contextunknown

Solar Pro 4

Solar Pro 4 is a large language model from Upstage built for enterprise workflow...

API IDupstage-solar-pro-4
Typeapi only
Parameters
Context524288

Qwen3.8 Max Preview

Preview Qwen flagship for million-token multimodal reasoning and long-horizon ag...

API IDalibaba-qwen3.8-max-preview
Typeapi only
Parameters
Context1M tokens

Nemotron 3 Ultra

NVIDIA Nemotron 3 Ultra is a flagship open-weight frontier LLM family engineered...

API IDnvidia-nemotron-3-ultra
Typeopen weights
Parameters550B total / 55B active
Context1M tokens

An experimental model using 4-bit weights and int8-convrot activations, with a VAE that speeds up decode times by ~1.5x, built by Comfy-Org.