infosave/MiniMax-H3-Turbo-cmf
text-to-video model by infosave
Older snapshot: check the original source for current information.
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
MiniMax-H3 renders video and synchronized stereo audio from one prompt, in one transformer, on two flow schedules. larryvrh's Turbo LoRA brings it to four sampling steps. This is both of them in the CMF container — the DiT, the Qwen3-VL prompt encoder, the video VAE decoder and the audio vocoder in a single memory-mapped file — running on cortiq, a Rust binary with no ML framework underneath. The reference checkout is 124.4 GB across four files plus a ComfyUI install. Here it is one file between 13.2 and 23.9 GB, and which one you take is decided by your VRAM. "A corgi in a chef hat flipping a pancake, sizzling sounds and a cheerful bark." — 512×288, 39 frames, seed 42, four steps, nothing but the prompt. The 13.2 GB file is the one to take if you have 16–20 GB of VRAM: it holds the whole run resident instead…
Read the full model card ↗ · Preview checked 2026-10-29T01:07:42.173Z
Inside the original model card — Document outline
- MiniMax-H3 Turbo — one file, no Python
- Same prompt, three files
- Which file
- Keyframe to video
- Running it
- 1. Get the runtime
- 2. Get the weights
- 3. Render
- Options that matter
- What it needs
- Field notes: 24 GB Macs and 20 GB cards
- Draft small, refine big (two-stage with LTX-2.5)
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
infosave/MiniMax-H3-Turbo-cmf is a text-to-video model repository published by infosave on Hugging Face. The source reports the cortiq library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- text-to-video
- Library
- cortiq
- Recent downloads (30 days)
- 3,042
- Cumulative likes
- 12
- Hugging Face trending score
- 0
- Reported safetensors parameters
- Not reported
- Architecture
- Not reported
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2026-08-06T20:25:33.000Z
- Last modified
- 2026-08-22T04:43:14.000Z
Compatibility and lineage
Language coverage was not reported.
Reported base models: Comfy-Org/MiniMax-H3, larryvrh/MiniMax-H3-Turbo-Lora
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-09-30T06:39:15.661Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.
Related models
QuantStack/Wan2.2-TI2V-5B-GGUF
QuantStack/Wan2.2-T2V-A14B-GGUF