Qwen-Image 2.1
safetensors (as published) · Qwen/Qwen-Image-2.1
in-progress non-commercial
| Publisher | Qwen |
|---|---|
| Modality | text-to-image + editing |
| Parameters | 7.1B Card: 7B visual generation component (32 single-stream DiT layers); repo also holds the text encoder. Source: model card. |
| Format | safetensors (as published) |
| Size on disk | 30.86 GiB (33,134,949,561 bytes) |
| Estimated memory to run | ~37.1 GB (estimate; see method) |
| Native context | n/a |
| Engine | Diffusers (QwenImage21Pipeline) · recipe |
| License | qwen-research Qwen Research License: NON-COMMERCIAL purposes only (LICENSE file). |
| Archive folder | usb-media/image |
| Notes | Card: 7B visual generation component (32 single-stream DiT layers); repo also holds the text encoder. |
Where it runs
| Machine | Verdict | Budget used |
|---|---|---|
| Bosgame M5 (x1) | Fits | ~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) | Fits | ~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.