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

Best video models to run locally on a 48GB PC without a graphics card

A leaderboard of the best video models you can run locally on a computer with 48GB of RAM and no graphics card. Wan 2.2 I2V A14B is #1 right now, followed by HunyuanVideo 1.5 and Wan 2.2 A14B. Models are ranked by one score that combines 55 published benchmarks. Each model shows the download that fits and the command to run it.

9 models · scores combine 55 benchmarks · updated how it works · find a leaderboard · benchmark your machine
task[all tasks][text to video][image to video][video editing]
Models for 48GB RAM · no GPU → ~35GB for models (CPU, slow) · local only · reset
+ more

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?ram=48&gpu=none&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

#modelscore↓where↓speed↓RAM↓get itsources
#modelscore↓where↓speed↓RAM↓get itsources
42Wan 2.2 I2V A14B · gguf-q4_k_m ×2 experts + umt5 q8_0 (sd.cpp) Alibaba56±2local (slow)~31GBhow to run › WorldReasonBench: Human-Aligned Stress Testing of Video Generators as Future World-State Predictors (arXiv v1)CRONOS: Benchmarking Counterfactual Physical Consistency in Video Models (arXiv:2605.23699v1), Table 1PAI-Bench: A Comprehensive Benchmark For Physical AI (arXiv:2512.01989v1)MindWorldBench: Evaluating Mental-State-to-Behavior Reasoning in Image-to-Video Generation (arXiv:2609.39147v1)Cosmos 3: Omnimodal World Models for Physical AI (arXiv:2606.02800v4)VGI-Bench: Probing Visual Intelligence in Video Generation Models+2
59HunyuanVideo 1.5 · fp16 720p T2V + Qwen2.5-VL q8_0 (sd.cpp) Tencent52±2local (slow)~34GBhow 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 ModelsVideoArgus: Agentic Rubric-Grounded Unified Evaluation for Video Generation and Editing (arXiv:2608.05485v1)Sci-VBench: Evaluating Knowledge- and Reasoning-Intensive Video Generation in Science DomainsHumanScore: Benchmarking Human Motions in Generated Videos
67Wan 2.2 A14B · gguf-q4_k_m ×2 experts + umt5 q8_0 (sd.cpp) Alibaba50±2local (slow)~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?VideoArgus: Agentic Rubric-Grounded Unified Evaluation for Video Generation and Editing (arXiv:2608.05485v1)
80Wan 2.1 14B · gguf-q8_0 + umt5 q8_0 (sd.cpp) Alibaba47±2local (slow)~27GBhow 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 GenerationWan-AI/Wan2.1-T2V-14B model cardAlibaba Wan technical report (arXiv:2503.20314v2), VBench table (own models)
81Wan 2.2 TI2V 5B · fp16 + umt5 q8_0 (sd.cpp) Alibaba47±2local (slow)~21GBhow to run › Cosmos 3: Omnimodal World Models for Physical AI (arXiv:2606.02800v4)VABench: A Comprehensive Benchmark for Audio-Video Generation (arXiv:2512.09299v2)Target-Bench: Can Video World Models Achieve Mapless Path Planning with Semantic Targets?VideoArgus: Agentic Rubric-Grounded Unified Evaluation for Video Generation and Editing (arXiv:2608.05485v1)Sci-VBench: Evaluating Knowledge- and Reasoning-Intensive Video Generation in Science DomainsPAI-Bench: A Comprehensive Benchmark For Physical AI (arXiv:2512.01989v1)+3
99Wan 2.1 T2V 1.3B · fp16 + umt5 q8_0 (sd.cpp) Alibaba40±4local (slow)~12GBhow 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
112LTX-2.3 · gguf-ud-q4_k_m 22B dev + Gemma 3 12B q4 (sd.cpp) Lightricks36±3local (slow)~34GBhow to run › WorldReasonBench: Human-Aligned Stress Testing of Video Generators as Future World-State Predictors (arXiv v1)MindWorldBench: Evaluating Mental-State-to-Behavior Reasoning in Image-to-Video Generation (arXiv:2609.39147v1)Sci-VBench: Evaluating Knowledge- and Reasoning-Intensive Video Generation in Science DomainsPhyGround: Benchmarking Physical Reasoning in Generative World Models (arXiv:2605.10806v1)
123LTX-Video 0.9 (2B) · openvino-int8 (OpenVINO GenAI, one-time export) Lightricks32±3*local (slow)~35GBhow to run › GenAI-Arena (TIGER-Lab) text-to-video leaderboard
—AnimateDiff SD 1.5 v2 motion adapter · fp32 motion module + SD 1.5 (sd.cpp) AnimateDiff authorsno reviewed resultslocal (slow)~7.8GBhow to run ›

+ 133 more don't fit your machine or budget · show them

142 of 142 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