Wan 2.2 I2V A14B
safetensors (as published) · Wan-AI/Wan2.2-I2V-A14B
queued
| Publisher | Wan-AI |
|---|---|
| Modality | image-to-video |
| Parameters | unknown Card: MoE image-to-video, A14B. Total params not stated: unknown. Source: model card. |
| Format | safetensors (as published) |
| Size on disk | 117.54 GiB (126,205,359,703 bytes) |
| Estimated memory to run | ~130.2 GB (estimate; see method) Same offload flags as T2V on the card. |
| Native context | n/a |
| Engine | Wan2.2 generate.py / ComfyUI · recipe |
| License | apache-2.0 Apache 2.0: commercial OK. |
| Archive folder | usb-media/video |
| Notes | Card: MoE image-to-video, A14B. Total params not stated: unknown. |
Where it runs
| Machine | Verdict | Budget used |
|---|---|---|
| Bosgame M5 (x1) | Tight / offload | ~108-110 GB GPU-usable on Linux with GTT raised (96 GB cap on Windows). Fit budget used here: 108 GB. |
| Bosgame M5 (x2, RPC) | Tight / offload | ~200-225 GB usable across two nodes. Fit budget used here: 210 GB; 210-225 GB = tight. |
| MacBook Pro (M4 Max) | No | macOS caps GPU wired memory by default (~75% = ~27 GB). Raising iogpu.wired_limit_mb to ~32 GB is possible but leaves little for the OS. |
| Mac mini (M4) | No | ~2/3 of 16 GB usable by the GPU by default. Already busy as build box + Hermes/Ollama. |
| omarchy (AMD desktop) | No | 7 GB of the 8 GB VRAM for weights. Offload capacity depends on system RAM, which is unknown today; after the 128 GB upgrade ~110 GB of MoE experts could sit in RAM. |
| Ugreen DXP2800 NAS | No | Storage host. Already runs ollama/open-webui containers; only tiny models (e.g. Whisper on CPU) are realistic. |
| MacBook Neo | Unknown | Specs unknown: machine was offline/unreachable on Nov 14 2026. |
Token/s = theoretical ceiling from memory bandwidth and active weight bytes; not a benchmark. Nothing on this page is a benchmark score.