Model reference · open weights

Minimax-H3-pruned

Minimax-H3-pruned is an open-weight video model from PurpleBlazey, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.

Video PurpleBlazey 1 variants 1k downloads/mo
Request this model on EU hardware All served models Not on the shared API today — deployed on request.

About

What Minimax-H3-pruned is

Made these for personal experimentation in KoboldCPP's sdui interface: https://github.com/LostRuins/koboldcpp/releases/latest Video/Image Model Minimax H3 was quanted with sd-cli.exe: https://github.com/leejet/stable-diffusion.cpp In theory, pruning is lossless for inference, and only negatively affects training. Text Encoder/Clip-1 File Qwen3VL-32b had layers 50 to 63 pruned to save on VRAM, which are unused for video encoding. All K and IQ quants use imatrix. All UD quants use modified tensor profiles based on: https://huggingface.co/unsloth/Qwen3-VL-32B-Instruct-GGUF Image/Video VAE and Audio VAE Cloned from here for convenience: https://huggingface.co/Comfy-Org/MiniMax-H3/tree/main/vae From my testing, the Qwen3VL text encoders work surprisingly well even at UD-IQ1M. The Minimax H3 quants took at least Q3K to become usable. Q2K is a meme quant, but maybe adding enough steps can salvage something decent? After Q4K, quality bumps become less noticable. I find Q5K is the quality sweetspot while allowing VRAM room for resolution & video length. Qwen3VL-32b-Heretic is an experimental quant of https://huggingface.co/llmfan46/Qwen3-VL-32B-Instruct-ultra-uncensored-heretic I can confirm it works with Minimax H3, but I'd recommend a non-heretic version actually intended for it first.

Summarised from the published model card. Read the full card on the HuggingFace links below.

Specifications

What it is

MakerPurpleBlazey
TypeVideo models
Variants1
Based onMiniMaxAI/MiniMax-H3, Comfy-Org/MiniMax-H3
Released2026-08-20
Popularity1k downloads / month
LicenceOpen weights

How it works

How video models work

Prompt / imagestart pointTemporal diffusionframes over timeVideoMP4 clipA video model generates a sequence of coherent frames from your prompt or a starting image.

Variants

Sizes & precisions

Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.

VariantParamsPrecisionVRAMFits 16 GBWeights
Minimax-H3-pruned-GGUFGGUFWeights ↗

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys purpleblazey-minimax-h3-pruned for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (purpleblazey-minimax-h3-pruned below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/videos/generations \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"purpleblazey-minimax-h3-pruned","prompt":"a drone shot over a forest"}'

Details

Languages, data & research

Languages

en

Tags

gguf imatrix image-text-to-video en

Licence

Open weights

Open weights under apache-2.0 — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗

Sources

Weights & code

Want Minimax-H3-pruned on EU-owned hardware?

Request this model on EU hardware See what’s served now

Explore

More video models

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms