ddalcu/MiniMax-H3-FL2VA-MLX-Serve-4bit
text-to-video model by ddalcu
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.
4-bit affine (group size 64) conversion of MiniMax-H3's FL2VA checkpoint for mlx-serve, running natively on Apple Silicon. Text-to-audio-video: the DiT denoises video and stereo audio jointly in one packed sequence. Self-contained: weights, both VAEs and the tokenizer in one directory. Upstream splits these across Comfy-Org/MiniMax-H3 (weights, no tokenizer) and MiniMaxAI/MiniMax-H3 (tokenizer). Quantized: the DiT and text-encoder matmul weights. Kept dense: gathered embedding tables, the checkpoint's fp32 islands (patch projections, output heads, time embedder) and both VAEs. Note that quantization here buys FOOTPRINT, not speed — the workload is compute-bound at roughly 192,000 FLOPs per weight byte. These are MODIFIED files. The transformer and text encoder are quantized to 4-bit; see MODIFICATIONS.md for the full list. The VAEs and tokenizer are unmodified copies. turbolora.safetensors is included. It is a 4-step distillation adapter trained by larryvrh and licensed Apache-2.0, copied byte for byte from that repo's minimaxh3turbo4stepemackpt850.safetensors and renamed so mlx-serve finds…
Read the full model card ↗ · Preview checked 2026-10-29T00:00:44.284Z
Inside the original model card — Document outline
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Documentation belongs to its respective authors. Reported project/model license: other. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
ddalcu/MiniMax-H3-FL2VA-MLX-Serve-4bit is a text-to-video model repository published by ddalcu on Hugging Face. The source reports the mlx 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
- mlx
- Recent downloads (30 days)
- 2,439
- Cumulative likes
- 8
- Hugging Face trending score
- 1
- Reported safetensors parameters
- Not reported
- Architecture
- Not reported
- License
- other
- Access
- Not gated by Hugging Face
- Created
- 2026-08-03T12:39:44.000Z
- Last modified
- 2026-08-07T04:01:25.000Z
Compatibility and lineage
Language coverage was not reported.
Reported base models: MiniMaxAI/MiniMax-H3
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 2026-09-15T06:34:04.920Z. 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