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

Best video editing models for a 64GB graphics card

A leaderboard of the best video editing models for a 64GB graphics card (with 32GB of system RAM). The best one that runs on it right now is MiniMax H3. Models are ranked on human votes comparing their video edits. Models that run on it show the download that fits and the command to run it.

9 models · scores combine 1 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 video editing evaluations only. Compare scores within this task. Models without task measurements are excluded.

Models for 32GB RAM · 64GB graphics card → ~64GB fast · 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=32&gpu=card&vram=64"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]
vram[1][2][4][8][12][16][24][32][48][64][80][96][128][160]GB
price[local][$0.05][$0.1][$0.25][any]max per sec

detecting your OS…

Score vs API price

#modeltask score↓where↓speed↓RAM↓get itsources
#modeltask score↓where↓speed↓RAM↓get itsources
1Wan 3.0 Alibaba68±9*api $0.10/secwww.alibabacloud.com ↗LMArena leaderboard dataset
2Dreamina Seedance 2.5 ByteDance67±9*api $0.30/secdocs.dev.runwayml.com ↗LMArena leaderboard dataset
3MiniMax H3 · gguf-q4_k_m fl2va + Qwen3-VL 32B q4_k_m (sd.cpp) MiniMax64±9*local~52GBhow to run › LMArena leaderboard dataset
4Gemini Omni Flash Google59±9*api $0.10/secai.google.dev ↗LMArena leaderboard dataset
5Dreamina Seedance 2.0 ByteDance Seed59±9*api $0.30/secfal.ai ↗LMArena leaderboard dataset
6HappyHorse 1.0 Alibaba-ATH49±9*api $0.14/secreplicate.com ↗LMArena leaderboard dataset
7Grok Imagine Video xAI40±9*api $0.050/secdocs.x.ai ↗LMArena leaderboard dataset
8Kling O3 Pro Kuaishou (Kling AI)39±9*api $0.11/secfal.ai ↗LMArena leaderboard dataset
9Kling O1 Pro Kuaishou (Kling AI)29±9*api $0.11/secreplicate.com ↗LMArena leaderboard dataset

+ 1 more don't fit your machine or budget · show them

10 of 10 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