whatmodel.sh · find the best video models you can run

Best text-to-video models to run locally

A leaderboard of the best text-to-video models you can run on your own computer. MiniMax H3 is #1 right now, followed by Cosmos3-Super and Kandinsky 5.0 Pro. Models are ranked on human votes and video generation tests. Each model shows the download that fits and the command to run it.

42 models · scores combine 25 benchmarks · updated how it works · find a leaderboard · benchmark your machine
task[all tasks][text to video][image to video][video editing]

Scores use reviewed text to video evaluations only. Compare scores within this task. Models without task measurements are excluded.

Filter by your hardware and budget · local only · reset
+ more
set[all sets][LMArena video · 94][VABench T2AV micro Visual QA · 3]

Filter the model list while keeping task scores. Models without a shared score scale are not yet calibrated; select a set to see its own scores.

Detect your exact chip or graphics card:

curl -G whatmodel.sh/video -d max=0 --data-urlencode "mac=$(sysctl -n hw.memsize machdep.cpu.brand_string)"Mac

curl -G whatmodel.sh/video -d max=0 --data-urlencode "ram=$(awk '/MemT/{print $2}' /proc/meminfo)" --data-urlencode "nv=$(nvidia-smi --query-gpu=name,memory.total --format=csv,noheader 2>/dev/null)"Linux

curl.exe -G whatmodel.sh/video -d max=0 --data-urlencode "ram=$((gcim Win32_ComputerSystem).TotalPhysicalMemory)" --data-urlencode "nv=$(nvidia-smi --query-gpu=name,memory.total --format=csv,noheader 2>$null)"Windows

$ terminal

detecting your OS…

Run curl "whatmodel.sh/video?max=0"to get this list in your terminal (add &format=json for agents).

ram[8][16][24][32][48][64][96][128][192][256]GB
gpu[apple silicon][graphics card][none]
price[local][$0.02][$0.05][$0.1][$0.25][any]max per sec

detecting your OS…

Score vs memory to run

#modeltask score↓where↓speed↓RAM↓get itsources
#modeltask score↓where↓speed↓RAM↓get itsources
8MiniMax H3 MiniMax76±2*local~40GBhow to run › LMArena leaderboard datasetSci-VBench: Evaluating Knowledge- and Reasoning-Intensive Video Generation in Science Domains
27Cosmos3-Super NVIDIA58±5*†local~160GBhow to run › Cosmos 3: Omnimodal World Models for Physical AI (arXiv:2606.02800v4)
34Kandinsky 5.0 Pro Sber54±2*local~76GBhow to run › LMArena leaderboard datasetHumanScore: Benchmarking Human Motions in Generated Videos
35Cosmos3-Nano NVIDIA54±4*local~42GBhow to run › Cosmos 3: Omnimodal World Models for Physical AI (arXiv:2606.02800v4)Sci-VBench: Evaluating Knowledge- and Reasoning-Intensive Video Generation in Science Domains
36HunyuanVideo 1.5 Tencent54±2local~20GBhow to run › LMArena leaderboard datasetCosmos 3: Omnimodal World Models for Physical AI (arXiv:2606.02800v4)WorldJen: An End-to-End Multi-Dimensional Benchmark for Generative Video ModelsSci-VBench: Evaluating Knowledge- and Reasoning-Intensive Video Generation in Science DomainsHumanScore: Benchmarking Human Motions in Generated Videos
40LongCat-Video Meituan53±7*local~100GBhow to run › Sci-VBench: Evaluating Knowledge- and Reasoning-Intensive Video Generation in Science Domains
41LTX-2 Lightricks53±2*local~120GBhow to run › LMArena leaderboard datasetWorldJen: An End-to-End Multi-Dimensional Benchmark for Generative Video Models
42Wan 2.2 A14B Alibaba52±2local~31GBhow to run › LMArena leaderboard datasetCosmos 3: Omnimodal World Models for Physical AI (arXiv:2606.02800v4)WorldJen: An End-to-End Multi-Dimensional Benchmark for Generative Video ModelsVideoVerse: Does Your T2V Generator Have World Model Capability to Synthesize Videos?
44Wan 2.1 14B Alibaba50±2local~20GBhow to run › VideoPhy / VideoPhy-2 official repository leaderboardsSkyReels-V2: Infinite-length Film Generative ModelCosmos 3: Omnimodal World Models for Physical AI (arXiv:2606.02800v4)T2VPhysBench: A First-Principles Benchmark for Physical Consistency in Text-to-Video GenerationAlibaba Wan technical report (arXiv:2503.20314v2), VBench table (own models)
46Kandinsky 5.0 T2V Lite Sber49±2*local~29GBhow to run › LMArena leaderboard dataset
47LTX-2 19B Distilled Lightricks49±7*local~41GBhow to run › Sci-VBench: Evaluating Knowledge- and Reasoning-Intensive Video Generation in Science Domains
48Cosmos-1.0-Diffusion-7B-Text2World NVIDIA48±3local~30GBhow to run › VideoPhy / VideoPhy-2 official repository leaderboardsCosmos World Foundation Model Platform for Physical AI (arXiv:2501.03575v3)
52Wan 2.2 TI2V 5B Alibaba47±4local~6.5GBhow to run › Cosmos 3: Omnimodal World Models for Physical AI (arXiv:2606.02800v4)VABench: A Comprehensive Benchmark for Audio-Video Generation (arXiv:2512.09299v2)Sci-VBench: Evaluating Knowledge- and Reasoning-Intensive Video Generation in Science Domains
53CogVideoX-5B Zhipu AI (THUDM)47±2local~13GBhow to run › VideoPhy / VideoPhy-2 official repository leaderboardsGenAI-Arena (TIGER-Lab) text-to-video leaderboardHumanScore: Benchmarking Human Motions in Generated Videos
57Pyramid Flow (SD3) Peking University / Kuaishou45±3*local~8GBhow to run › GenAI-Arena (TIGER-Lab) text-to-video leaderboard
58T2V-Turbo-v2 UC Santa Barbara45±7*†local~9.4GBhow to run › T2V-Turbo-v2: Enhancing Video Generation Model Post-Training through Data, Reward, and Conditional Guidance Design (arXiv 2410.05677v3)
59Open-Sora 2.0 HPC-AI Tech45±5*local~55GBhow to run › VideoVerse: Does Your T2V Generator Have World Model Capability to Synthesize Videos?SkyReels-V2: Infinite-length Film Generative Model
61Wan 2.1 T2V 1.3B Alibaba43±4local~8.6GBhow to run › WorldJen: An End-to-End Multi-Dimensional Benchmark for Generative Video ModelsAlibaba Wan technical report (arXiv:2503.20314v2), VBench table (own models)Training-Free Efficient Video Generation via Dynamic Token Carving
62LTX-2.3 Lightricks43±7*local~34GBhow to run › Sci-VBench: Evaluating Knowledge- and Reasoning-Intensive Video Generation in Science Domains
63Mochi 1 Genmo42±2local~6.5GBhow to run › LMArena leaderboard datasetGenAI-Arena (TIGER-Lab) text-to-video leaderboardVideoPhy / VideoPhy-2 official repository leaderboardsT2VPhysBench: A First-Principles Benchmark for Physical Consistency in Text-to-Video Generation
65HunyuanVideo Tencent41±3local~28GBhow to run › VideoPhy / VideoPhy-2 official repository leaderboardsSkyReels-V2: Infinite-length Film Generative ModelVideoVerse: Does Your T2V Generator Have World Model Capability to Synthesize Videos?Training-Free Efficient Video Generation via Dynamic Token Carving
68T2V-Turbo (VC2) UC Santa Barbara41±3†local~9.4GBhow to run › GenAI-Arena (TIGER-Lab) text-to-video leaderboardT2V-Turbo-v2: Enhancing Video Generation Model Post-Training through Data, Reward, and Conditional Guidance Design (arXiv 2410.05677v3)T2V-Turbo: Breaking the Quality Bottleneck of Video Consistency Model with Mixed Reward Feedback (arXiv:2405.18750v2)
70CogVideoX-2B Zhipu AI (THUDM)39±2local~5.3GBhow to run › VideoPhy / VideoPhy-2 official repository leaderboardsGenAI-Arena (TIGER-Lab) text-to-video leaderboardChronoMagic-Bench: A Benchmark for Metamorphic Evaluation of Text-to-Time-lapse Video Generation
71CogVideoX1.5-5B Zhipu AI (THUDM)38±3local~38GBhow to run › LOVE: Benchmarking and Evaluating Text-to-Video Generation and Video-to-Text Interpretation (AIGVE-60K)VideoVerse: Does Your T2V Generator Have World Model Capability to Synthesize Videos?SkyReels-V2: Infinite-length Film Generative ModelSci-VBench: Evaluating Knowledge- and Reasoning-Intensive Video Generation in Science Domains
72Allegro Rhymes AI38±2local~9.3GBhow to run › LOVE: Benchmarking and Evaluating Text-to-Video Generation and Video-to-Text Interpretation (AIGVE-60K)GenAI-Arena (TIGER-Lab) text-to-video leaderboard
73VideoCrafter2 Tencent AI Lab37±2local~9.4GBhow to run › VideoPhy / VideoPhy-2 official repository leaderboardsLOVE: Benchmarking and Evaluating Text-to-Video Generation and Video-to-Text Interpretation (AIGVE-60K)GenAI-Arena (TIGER-Lab) text-to-video leaderboardChronoMagic-Bench: A Benchmark for Metamorphic Evaluation of Text-to-Time-lapse Video Generation
76LaVie (base T2V) Shanghai AI Lab (Vchitect)35±2local~4.9GBhow to run › LOVE: Benchmarking and Evaluating Text-to-Video Generation and Video-to-Text Interpretation (AIGVE-60K)VideoPhy / VideoPhy-2 official repository leaderboardsGenAI-Arena (TIGER-Lab) text-to-video leaderboardChronoMagic-Bench: A Benchmark for Metamorphic Evaluation of Text-to-Time-lapse Video Generation
77LTX-Video 0.9 (2B) Lightricks35±3*local~5.3GBhow to run › GenAI-Arena (TIGER-Lab) text-to-video leaderboard
79Open-Sora 1.1 HPC-AI Tech34±6*local~14GBhow to run › ChronoMagic-Bench: A Benchmark for Metamorphic Evaluation of Text-to-Time-lapse Video Generation
81NOVA-0.6B T2V BAAI32±3*local~9.3GBhow to run › LOVE: Benchmarking and Evaluating Text-to-Video Generation and Video-to-Text Interpretation (AIGVE-60K)
82Hotshot-XL Hotshot31±2local~10GBhow to run › EvalCrafter: original 2023 text-to-video evaluationsLOVE: Benchmarking and Evaluating Text-to-Video Generation and Video-to-Text Interpretation (AIGVE-60K)
85ZeroScope v2 576w cerspense30±3local~7.9GBhow to run › VideoPhy / VideoPhy-2 official repository leaderboardsChronoMagic-Bench: A Benchmark for Metamorphic Evaluation of Text-to-Time-lapse Video GenerationFETV: A Benchmark for Fine-Grained Evaluation of Open-Domain Text-to-Video Generation (arXiv:2311.01813v3)
87VideoCrafter1 T2V Tencent AI Lab / HKUST29±2local~8.1GBhow to run › EvalCrafter: original 2023 text-to-video evaluations
88Show-1 Show Lab / NUS29±2local~83GBhow to run › EvalCrafter: original 2023 text-to-video evaluations
89Open-Sora 1.2 HPC-AI Tech28±3*local~39GBhow to run › GenAI-Arena (TIGER-Lab) text-to-video leaderboardChronoMagic-Bench: A Benchmark for Metamorphic Evaluation of Text-to-Time-lapse Video Generation
90ModelScope T2V 1.7B Alibaba DAMO Academy28±2local~4.6GBhow to run › EvalCrafter: original 2023 text-to-video evaluationsLOVE: Benchmarking and Evaluating Text-to-Video Generation and Video-to-Text Interpretation (AIGVE-60K)GenAI-Arena (TIGER-Lab) text-to-video leaderboardChronoMagic-Bench: A Benchmark for Metamorphic Evaluation of Text-to-Time-lapse Video GenerationFETV: A Benchmark for Fine-Grained Evaluation of Open-Domain Text-to-Video Generation (arXiv:2311.01813v3)
91LVDM (text-to-video) HKUST / Tencent AI Lab28±3*local~6.1GBhow to run › LOVE: Benchmarking and Evaluating Text-to-Video Generation and Video-to-Text Interpretation (AIGVE-60K)
93ZeroScope v2 XL (576w → XL pipeline) cerspense27±2local~15GBhow to run › EvalCrafter: original 2023 text-to-video evaluations
94CogVideo 9B (original) Tsinghua / Zhipu26±7*local~52GBhow to run › FETV: A Benchmark for Fine-Grained Evaluation of Open-Domain Text-to-Video Generation (arXiv:2311.01813v3)
—Kandinsky 6.0 Video Lite Sbernot yet calibratedlocal~34GBhow to run › Kandinsky 6.0 Video: Foundation Models for Synchronized Video and Audio Generation (arXiv:2610.05608v1)
—Kandinsky 6.0 Video Pro Sbernot yet calibratedlocal~109GBhow to run › Kandinsky 6.0 Video: Foundation Models for Synchronized Video and Audio Generation (arXiv:2610.05608v1)
—LTX-2.5 Lightricksnot yet calibratedlocal~14GBhow to run › Kandinsky 6.0 Video: Foundation Models for Synchronized Video and Audio Generation (arXiv:2610.05608v1)

+ 55 more don't fit your machine or budget · show them

97 of 97 catalogue models listed here · sources and licences

* new or thinly tested: ranked on too few benchmark results · † only the maker’s own numbers so far · ~RAM is estimated; full context may need more memory