Model reference · open weights
minimax-h3-convrot is an open-weight video model from rockerBOO, 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.
About
MiniMax H3 — NVFP4 / INT4 quants for ComfyUI Quantized diffusion transformers for MiniMax H3, a 33B omni-modal video+audio generator, built from the ComfyUI repack at Comfy-Org/MiniMax-H3. Output is 768p / 24 fps / 4–15 s with synchronized 32 kHz stereo audio. (2K output requires the separate H3-Regenerate-2K module, which is not part of this or Comfy-Org's release.) These are ComfyUI single-file checkpoints, not diffusers models. Which file do I want? Filenames follow minimaxh3<fl2va|ref2va<variant.safetensors. - fl2va — first/last-frame mode. Zero images = text-to-video, one or two = frame-conditioned. - ref2va — omni-reference mode (up to 9 images / 3 video clips / 3 audio clips). Both get identical treatment; pick the one matching your workflow. The three INT4 variants exist for fl2va only. All other variants exist for both. Tradeoffs at a glance - NVFP4 needs Blackwell (SM ≥ 10.0/12.0 — RTX 50-series, B100/B200). No fallback on older cards. This applies to every nvfp4 file, including the convrotint8 ones, which are NVFP4 everywhere except attn.qkvproj. - Pruned vs. unpruned — pruning replaces the AdaLN modulation network (~40% of parameters) with a precomputed lookup table. Comfy-Org reports no quality loss, and it's a 34 GB → 20 GB cut. The tradeoff is that it depends on ComfyUI's shape-based detection of the pruned architecture, so the unpruned files are the safer choice outside ComfyUI. - INT4 is the escape hatch for non-Blackwell GPUs, at the cost of unvalidated quality. It needs a ComfyUI build with comfy-kitchen's TensorCoreConvRotW4A4Layout. Note that comfy-kitchen's W4A4 CUDA kernel only uses native INT4 tensor-core MMA on major == 8 (Ampere/Ada); Blackwell always falls through to an INT8-activation path, so there is no speed argument for INT4 there. - The mixed INT4/INT8 file is the same 20 GB as prunednvfp4. It is only worth choosing if you can't run NVFP4 — it trades away validated quality for nothing else. - Quality has not been measured anywhere in this repo. The NVFP4 files are recommended because they use conservative, established formats and are confirmed working, not because of a benchmark. The INT4 files are confirmed only to load and gene
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | rockerBOO |
|---|---|
| Type | Video models |
| Variants | 1 |
| Runs with | minimax-h3 |
| Based on | MiniMaxAI/MiniMax-H3 |
| Released | 2026-08-03 |
| Popularity | 53k downloads / month |
| Likes | 27 |
| Licence | Commercial licence needed |
How it works
Variants
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.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| minimax-h3-nvfp4-convrot | — | NVFP4 | — | — | Weights ↗ |
Using it via the API
Once AxForge deploys rockerboo-minimax-h3-convrot for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (rockerboo-minimax-h3-convrot 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":"rockerboo-minimax-h3-convrot","prompt":"a drone shot over a forest"}'
Licence
The weights are open but its licence needs a commercial agreement for business use. AxForge can arrange that licence and host the model for you — you pay AxForge, we settle with the model’s maker. Ask us for a quote. Read the licence ↗
Explore