Best video models for a 128GB graphics card
A leaderboard of the best video models for a 128GB graphics card (with 32GB of system RAM). The best one that runs on it right now is MiniMax H3, followed by Wan 2.2 I2V A14B and LTX-2.5. Models are ranked by one score that combines 55 published benchmarks. Models that run on it show the download that fits and the command to run it.
94 models · scores combine 55 benchmarks · updated how it works · find a leaderboard · benchmark your machine
Models for 32GB RAM · 128GB graphics card → ~128GB fast · reset
+ more
$ terminal
↗ share
detecting your OS…
Score vs API price
x
show
● open weights ◆ API only ─┘ best score for the price · x: USD per second of video (log)
| # | model | score↓ | where↓ | speed↓ | sources |
|---|---|---|---|---|---|
| 1 |  Gemini Omni 1.1 Flash | 81±2 | api $0.10/sec |    +1 | |
| 2 |  Wan 3.0 Prime | 80±7* | api $0.14/sec | | |
| 3 | Gemini Omni Flash | 80±2 | api $0.10/sec | | |
| 4 | Wan 3.0 | 79±2 | api $0.10/sec | | |
| 5 |  Dreamina Seedance 2.0 | 79±1 | api $0.30/sec | +3 | |
| 6 |  MiniMax H3 · gguf-q4_k_m fl2va + Qwen3-VL 32B q4_k_m (sd.cpp) | 78±1 | local | +2 | |
| 7 |  Dreamina Seedance 2.5 | 77±1 | api $0.30/sec | | |
| 8 |  FLUX 3 Video | 77±2 | api $0.17/sec | | |
| 9 | HappyHorse 1.1 | 76±3 | api $0.14/sec | | |
| 10 | MiniMax H3 Max | 76±4* | api $0.080/sec | | |
| 12 |  Grok Imagine Video 1.5 | 75±2 | api $0.080/sec | | |
| 14 | Wan 2.2 I2V Flash | 75±4* | api $0.036/sec | | |
| 15 |  HappyHorse 1.0 | 73±2 | api $0.14/sec | | |
| 16 | Wan 2.2 I2V Plus | 71±5* | api $0.10/sec | | |
| 17 | Grok Imagine Video | 69±2 | api $0.050/sec | | |
| 18 |  Kling 3.0 Pro | 69±2 | api $0.11/sec | | |
| 19 |  Veo 3.1 | 69±1 | api $0.40/sec | +11 | |
| 21 | Veo 3.1 Fast | 68±1 | api $0.10/sec | +1 | |
| 22 | Kling 3.0 | 68±4 | api $0.084/sec | | |
| 23 | Wan 2.7 | 68±2 | api $0.10/sec | | |
| 24 |  Vidu Q3 Pro | 65±2 | api $0.10/sec | | |
| 26 |  Runway Aleph 2.0 | 65±7* | api $0.28/sec | | |
| 28 | Wan 2.6 | 65±1 | api $0.10/sec | | |
| 31 | Kling O3 Pro | 64±4* | api $0.11/sec | | |
| 32 | Seedance 1.0 Pro Fast | 62±11* | api $0.049/sec | | |
| 33 | Wan 2.5 Preview | 61±2 | api $0.10/sec | | |
| 34 | Kling 2.6 Pro | 59±2 | api $0.070/sec | | |
| 35 |  PixVerse V5.6 | 59±2 | api $0.045/sec | | |
| 36 | Runway Gen-4.5 | 58±2 | api $0.12/sec | | |
| 37 | Wan 2.1 I2V Plus | 58±5* | api price unknown | | |
| 39 | Seedance 1.5 Pro | 58±2 | api $0.052/sec | | |
| 40 | Kling 2.5 Turbo Pro | 57±2 | api $0.070/sec | | |
| 42 | Wan 2.2 I2V A14B · gguf-q8_0 ×2 experts + umt5 q8_0 (sd.cpp) | 56±2 | local | +2 | |
| 43 | Seedance 1.0 Pro | 56±2 | api $0.052/sec | | |
| 44 | Kling O1 Pro | 56±2* | api $0.11/sec | | |
| 45 | Wan 2.6 Flash | 55±7* | api $0.025/sec | | |
| 46 |  P-Video | 55±2 | api $0.020/sec | | |
| 47 | Vidu Q2 Turbo | 55±3* | api $0.050/sec | | |
| 48 | Hailuo 2.3 | 55±2 | api $0.047/sec | | |
| 51 | Kling 2.1 Standard | 54±3* | api $0.050/sec | | |
| 52 | Hailuo 02 | 54±2 | api $0.047/sec | | |
| 53 |  LTX-2.5 · gguf-q8_0 22B dev + Gemma 4 12B q8_0 (sd.cpp) | 53±6* | local | | |
| 55 |  HunyuanVideo 1.5 (I2V) · bf16 480p I2V + model CPU offload | 53±2 | local | +2 | |
| 56 | Kling 2.1 Master | 53±2* | api $0.28/sec | | |
| 57 |  Kandinsky 5.0 Pro · bf16 + model CPU offload | 52±2* | local | | |
| 59 | HunyuanVideo 1.5 · fp16 720p T2V (sd.cpp) | 52±2 | local | | |
| 60 |  Cosmos3-Nano · bf16 | 52±3 | local | | |
| 61 | PixVerse 5.5 | 52±10* | api $0.060/sec | | |
| 63 |  LongCat-Video · bf16 | 51±2 | local | | |
| 64 | Kandinsky 6.0 Video Lite · bf16 + model CPU offload | 51±7*† | local | | |
| 67 | Wan 2.2 A14B · bf16 | 50±2 | local | | |
| 71 |  Open-Sora Plan v1.3 (T2V) · bf16 | 49±7* | local | | |
| 77 | Kandinsky 6.0 Video Pro · bf16 + model CPU offload | 48±7*† | local | | |
| 80 | Wan 2.1 14B · bf16 | 47±2 | local |  | |
| 81 | Wan 2.2 TI2V 5B · fp16 + umt5 q8_0 (sd.cpp) | 47±2 | local | +3 | |
| 82 | Kandinsky 5.0 T2V Lite · bf16 | 47±2* | local | | |
| 83 | LTX-2 19B Distilled | 47±8* | api $0.020/sec | | |
| 85 |  CogVideoX-5B-I2V · bf16 | 46±4 | local | | |
| 86 | Cosmos-1.0-Diffusion-7B-Text2World · bf16 | 46±3 | local | | |
| 87 | Hailuo 01 (MiniMax video-01 / I2V-01) | 46±4* | api $0.083/sec | | |
| 90 | HunyuanVideo-I2V · bf16 720p + CPU offload (official script) | 45±4 | local | | |
| 91 | CogVideoX-5B · bf16 | 44±2 | local | | |
| 93 | Wan 2.1 I2V Turbo | 43±7* | api price unknown | | |
| 95 |  Open-Sora 2.0 · bf16 256px text-to-image-to-video + offload (Flux first frame) | 42±5* | local | | |
| 96 |  Pyramid Flow (SD3) · bf16 | 42±3* | local | | |
| 99 | Wan 2.1 T2V 1.3B · fp16 + umt5 q8_0 (sd.cpp) | 40±4 | local | | |
| 100 |  Mochi 1 · bf16 | 40±2 | local | | |
| 102 | Open-Sora Plan v1.3 (I2V) · bf16 | 39±7* | local | | |
| 105 | HunyuanVideo · bf16 | 39±3 | local | | |
| 107 |  T2V-Turbo-v2 · fp32 | 38±5* | local | | |
| 109 | T2V-Turbo (VC2) · fp32 | 38±3† | local | | |
| 110 | Runway Gen-4 Turbo | 37±3* | api $0.050/sec | | |
| 112 | LTX-2.3 · gguf-ud-q4_k_m 22B dev + Gemma 3 12B q4 (sd.cpp) | 36±3 | local | | |
| 113 | CogVideoX1.5-5B · bf16 + sequential CPU offload | 36±2 | local | | |
| 114 | CogVideoX-2B · fp16 | 36±2 | local | | |
| 115 |  Pika 2.2 | 36±2 | api $0.040/sec | | |
| 116 |  Allegro · bf16 | 35±2 | local | | |
| 118 |  VideoCrafter2 · fp32 | 34±2 | local | | |
| 121 | Open-Sora 1.1 · bf16 | 32±7* | local | | |
| 122 |  LaVie (base T2V) · fp16 | 32±2 | local | | |
| 123 | LTX-Video 0.9 (2B) · openvino-int8 (OpenVINO GenAI, one-time export) | 32±3* | local | | |
| 125 |  NOVA-0.6B T2V · fp16 | 29±3* | local | | |
| 126 | ZeroScope v2 576w · fp16 | 27±3 | local | | |
| 127 |  Hotshot-XL · fp16 | 27±2 | local | | |
| 130 | Open-Sora 1.2 · bf16 | 27±3 | local | | |
| 133 | VideoCrafter1 T2V · official script (checkpoint as stored) | 26±2 | local | | |
| 134 |  Show-1 · fp16 + model CPU offload (official run_inference.py) | 25±2 | local | | |
| 135 |  LVDM (text-to-video) · fp32 | 25±3* | local | | |
| 136 |  ModelScope T2V 1.7B · fp16 | 25±2 | local | | |
| 138 | ZeroScope v2 XL (576w → XL pipeline) · fp16 + model CPU offload (576w base, then XL vid2vid) | 24±2 | local | | |
| 139 | CogVideo 9B (original) · fp16 (--fp16), both stages | 23±7* | local | | |
| — | AnimateDiff SD 1.5 v2 motion adapter · fp32 motion module + SD 1.5 (sd.cpp) | no reviewed results | local | ||
| — |  Stable Video Diffusion (SVD, 14 frames) · fp16 · CPU offload | no reviewed results | local | ||
| — | Stable Video Diffusion XT (25 frames) · fp16 · CPU offload | no reviewed results | local |
+ 48 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