Best video models for 12 GB of VRAM
Which open-weight video models run on an NVIDIA GPU with 12 GB of VRAM. Verdicts come from exact Hugging Face file sizes, model card and app maker statements, and published runs.
- Run
- 6
- Unknown
- 1
- Fits with offload
- 0
- Exceeds VRAM
- 0
6 of 7 listed video models run on an NVIDIA GPU with 12 GB of VRAM: MiniMax H3, HunyuanVideo-1.5, Wan2.2 A14B, LTX-2.3, LTX-2.5 and Wan2.2 TI2V 5B. Highest blind-vote rank among them: MiniMax H3, #8 of 48 in text to video (Arena, snapshot 2026-09-22). No figure covers Mochi 1 preview at this size yet.
License check before commercial use: MiniMax H3, HunyuanVideo-1.5, LTX-2.3, LTX-2.5.
Get the weekly local AI newsletter
The Thursday ModelFit newsletter: new local models and what fits your machine.
For: MacBook Air M5 16 GB
You'll also get the weekly ModelFit email. By signing up you agree to our Privacy Policy. Unsubscribe from either email anytime, in one click.
Which video models run on an NVIDIA GPU with 12 GB of VRAM?
7 modelsRuns means a model card, app maker or NVIDIA figure, or a dated run on a named card, at or below 12 GB. Fits with offload means the main model weights fit in 12 GB with a 15% margin but the full set does not: the text encoder and VAE run from system RAM, which is slower. Exceeds VRAM means even the main weights are too large for the card. Mac runs never count here. unknown means no source covers this size yet; it is not a failure.
| Model | Verdict | Why | Quality | App |
|---|---|---|---|---|
| MiniMax H3MiniMax H3 Community License Agreement | Runs · Stated | Stated by the source: 12 GB of VRAM runs it (Diffusers int8, streamed blocks, 960x544, about 75 GB system RAM).Diffusers docs: MiniMax-H3 memory | #8 of 48 in text to video11,417 votes | stable-diffusion.cpp, ComfyUI |
| HunyuanVideo-1.5Tencent Hunyuan Community License | Runs · Published | A dated run on RTX 4070 with 12 GB of VRAM: ComfyUI example workflow, 480p I2V distilled fp8, 81 frames.ComfyUI issue #10855 | #38 of 48 in text to video4,292 votes | ComfyUI |
| Wan2.2 A14BApache License 2.0 | Runs · Published | A dated run on RTX 2060 with 6 GB of VRAM, below this 12 GB tier: ComfyUI Q8 GGUF, 480x720, 81 frames, 28 GB RAM plus a 60 GB page file.ComfyUI issue #12451 | #42 of 48 in text to video10,458 votes | ComfyUI |
| LTX-2.3LTX-2 Community License Agreement | Runs · Published | A dated run on RTX 4060 with 8 GB of VRAM, below this 12 GB tier: ComfyUI GGUF workflow, 720p 5 s, 32 GB RAM.ComfyUI issue #14345 | No independent score yet | Lightricks/LTX-2 ltx-pipelines, ComfyUI |
| LTX-2.5LTX-2.x Community License Agreement | Runs · Stated | Stated by the source: 12 GB of VRAM runs it (LTX Desktop on Windows, weight streaming, 40 GB RAM, 540p).LTX Desktop compatibility matrix (Lightricks) | No independent score yet | Lightricks/LTX-2 ltx-pipelines, ComfyUI |
| Wan2.2 TI2V 5BApache License 2.0 | Runs · Stated | Stated by the source: 8 GB of VRAM runs it, below this 12 GB tier (ComfyUI native offloading).ComfyUI docs: Wan2.2 | No independent score yet | ComfyUI |
| Mochi 1 previewApache License 2.0 | unknown | The smallest complete build, calcuis GGUF Q3_K_M with Q4_0 T5 and FP8 VAE, is a 7.7 GB download, but no stated figure or published run covers 12 GB of VRAM yet. | #48 of 48 in text to video5,893 votes | Diffusers, ComfyUI |
Quality: blind human votes from Arena (arena.ai), CC BY 4.0, snapshot 2026-09-22. Scores are for the Arena checkpoint, not your local quantized build.
Frequently asked questions
What is the best video model for an NVIDIA GPU with 12 GB of VRAM?
MiniMax H3 has the highest blind-vote rank among the video models that run on an NVIDIA GPU with 12 GB of VRAM: #8 of 48 in text to video, from 11,417 votes (Arena, snapshot 2026-09-22). HunyuanVideo-1.5, Wan2.2 A14B, LTX-2.3, LTX-2.5 and Wan2.2 TI2V 5B also run.
Which video models run on an NVIDIA GPU with 12 GB of VRAM?
MiniMax H3 (12 GB stated by Diffusers docs: MiniMax-H3 memory), HunyuanVideo-1.5 (run on RTX 4070 with 12 GB), Wan2.2 A14B (run on RTX 2060 with 6 GB), LTX-2.3 (run on RTX 4060 with 8 GB), LTX-2.5 (12 GB stated by LTX Desktop compatibility matrix (Lightricks)) and Wan2.2 TI2V 5B (8 GB stated by ComfyUI docs: Wan2.2).
Which video models are not confirmed on an NVIDIA GPU with 12 GB of VRAM?
Mochi 1 preview (calcuis GGUF Q3_K_M with Q4_0 T5 and FP8 VAE, 7.7 GB). No stated figure or published run covers this size yet, which is not the same as a failure.