All models › genmo
mochi-v1
genmo · Apache 2.0 license · on Arena since 7 Aug 2025
Download
Arena score1007#48 of 48 in Video, paid models included
Size10 Bparameters
4-bit download6.1 GBweights only, Q4_K_M
Max context—
Where to use it for free
- Download and run it at home: official weights · GGUF files for Ollama and LM Studio
Arena scores
| Arena | Score | Rank | Votes |
|---|---|---|---|
| Video | 1007 | #48 of 48 | 6K |
Rank among all models, paid ones included. Source: Arena leaderboard dataset.
Does it fit on popular hardware?
| Hardware | GPU memory | Fits? |
|---|---|---|
| RTX 3060 12 GB | 12 GB | Fits in GPU |
| RTX 4060 Ti 16 GB | 16 GB | Fits in GPU |
| RTX 3090 | 24 GB | Fits in GPU |
| RTX 4090 | 24 GB | Fits in GPU |
| RTX 5090 | 32 GB | Fits in GPU |
| RX 7900 XTX | 24 GB | Fits in GPU |
| 2 × RTX 3090 | 48 GB | Fits in GPU |
| 4 × RTX 3090 | 96 GB | Fits in GPU |
| Mac M4 Max 128 GB | 96 GB | Fits in GPU |
| Ryzen AI Max+ 395 128 GB | 96 GB | Fits in GPU |
| 8 × H100 SXM | 640 GB | Fits in GPU |
Estimate at 4-bit, 64 GB of DDR5 for offload. Speed ≈ memory bandwidth × 70% ÷ data read per token; real numbers vary by about ±30%.
GPU memory needed
| Level | Total |
|---|---|
| Q3_K_M | 8.6 GB |
| Q4_K_M | 9.7 GB |
| Q5_K_M | 11 GB |
| Q6_K | 12 GB |
| Q8_0 | 14 GB |
| F16 | 24 GB |
Weights + text encoders and decoder (about 3 GB) + runtime. Simulate your own setup.
Video score over time
100012001400
MayJunJulAugSept
mochi-v1 1007Best paid model
Arena score from 7 Apr 2026 to 22 Sept 2026.
Similar free models in Video
- kandinsky-5.0-t2v-lite 1113 · 2 B
- wan-v2.2-a14b 1132 · 27 B
- ltx-2-19b 1154 · 18.9 B
- hunyuan-video-1.5 1169 · 8.3 B
- kandinsky-5.0-t2v-pro 1175 · 19.3 B
- minimax-h3 1460 · 33.1 B