6block/MiniMax-H3-Qwen3-VL-NVFP4
text-to-video model by 6block
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.
An NVFP4 (4-bit) Qwen3-VL-32B text encoder for MiniMax-H3, made with convert-to-quant. It is a drop-in replacement for the H3 conditioning text encoder (ComfyUI CLIPLoader, type minimax). The H3 video weights are unchanged — only the text encoder is quantized to 4-bit, to bring the full H3 stack onto consumer GPUs. tower (--qwenvlm filter). The middle language-layer linears go to NVFP4 (FP4 E2M1, block 16). This encoder deliberately keeps more of the network in bf16 than a minimum-size 4-bit encoder does. The --qwenvlm filter protects — at bf16 — the token embeddings, the first and last language layers, and the entire vision tower, quantizing only the middle language-layer linears to NVFP4. The result is 16.64 GiB, about 2 GiB above the most aggressively quantized community NVFP4 encoders (≈14.6 GiB, e.g. the AWQ-quantized encoder in Comfy-Org/MiniMax-H3), in exchange for leaving the precision-sensitive layers (embeddings, boundary layers, vision) untouched. It is a fidelity-first…
Read the full model card ↗ · Preview checked 2026-10-31T14:13:21.188Z
Inside the original model card — Document outline
- MiniMax-H3-Qwen3-VL-NVFP4
- Quantization
- What's different
- Quantization fidelity (4-bit vs bf16)
- Verified
- Usage (ComfyUI)
- Notes
- Credits & license
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
6block/MiniMax-H3-Qwen3-VL-NVFP4 is a text-to-video model repository published by 6block on Hugging Face. The source reports the minimax-h3 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
- minimax-h3
- Recent downloads (30 days)
- 5,001
- Cumulative likes
- 0
- Hugging Face trending score
- 0
- Reported safetensors parameters
- Not reported
- Architecture
- Not reported
- License
- other
- Access
- Not gated by Hugging Face
- Created
- 2026-08-18T07:40:06.000Z
- Last modified
- 2026-08-21T02:47:50.000Z
Compatibility and lineage
Reported languages: en, zh
Reported base models: Comfy-Org/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 2026-10-27T06:48:24.124Z. 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