Best video models for 16 GB of VRAM
Which open-weight video models run on an NVIDIA GPU with 16 GB of VRAM. Verdicts come from exact Hugging Face file sizes, model card and app maker statements, and published runs.
- Run
- 7
- Unknown
- 1
- Fits with offload
- 0
- Exceeds VRAM
- 0
7 of 8 listed video models run on an NVIDIA GPU with 16 GB of VRAM: MiniMax H3, HunyuanVideo-1.5, Wan2.2 A14B, LTX-2.3, LTX-2.5, Wan2.1 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 16 GB of VRAM?
8 modelsRuns means a model card, app maker or NVIDIA figure, or a dated run on a named card, at or below 16 GB. Fits with offload means the main model weights fit in 16 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 · Published | A dated run on RTX 5060 with 16 GB of VRAM: ComfyUI int8 convrot with int4 text encoder, 1024x768, 10 s.ComfyUI issue #15274 | #8 of 48 in text to video11,417 votes | stable-diffusion.cpp, ComfyUI |
| HunyuanVideo-1.5Tencent Hunyuan Community License | Runs · Stated | Stated by the source: 14 GB of VRAM runs it, below this 16 GB tier (official runner with model offloading).HunyuanVideo-1.5 model card | #38 of 48 in text to video4,292 votes | ComfyUI |
| Wan2.2 A14BApache License 2.0 | Runs · Published | A dated run on RTX 5060 Ti with 16 GB of VRAM: ComfyUI fp16 I2V with 4-step LoRAs, 64 GB system RAM.ComfyUI issue #10662 | #42 of 48 in text to video10,458 votes | ComfyUI |
| LTX-2.3LTX-2 Community License Agreement | Runs · Stated | Stated by the source: 16 GB of VRAM runs it (distilled with FP8 cast, previews only).LTX blog: hardware for AI video models | 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, below this 16 GB tier (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 |
| Wan2.1Apache License 2.0 | Runs · Stated | Stated by the source: 13 GB of VRAM runs it, below this 16 GB tier (T2V 14B in Diffusers, bf16 with group offloading to system RAM).Diffusers docs: Wan pipeline | No independent score yet | ComfyUI |
| Wan2.2 TI2V 5BApache License 2.0 | Runs · Stated | Stated by the source: 8 GB of VRAM runs it, below this 16 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 16 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 16 GB of VRAM?
MiniMax H3 has the highest blind-vote rank among the video models that run on an NVIDIA GPU with 16 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, Wan2.1 and Wan2.2 TI2V 5B also run.
Which video models run on an NVIDIA GPU with 16 GB of VRAM?
MiniMax H3 (run on RTX 5060 with 16 GB), HunyuanVideo-1.5 (14 GB stated by HunyuanVideo-1.5 model card), Wan2.2 A14B (run on RTX 5060 Ti with 16 GB), LTX-2.3 (16 GB stated by LTX blog: hardware for AI video models), LTX-2.5 (12 GB stated by LTX Desktop compatibility matrix (Lightricks)), Wan2.1 (13 GB stated by Diffusers docs: Wan pipeline) and Wan2.2 TI2V 5B (8 GB stated by ComfyUI docs: Wan2.2).
Which video models are not confirmed on an NVIDIA GPU with 16 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.