Media generation

Qwen-Image-Flash

Qwen-Image distilled to four steps, guidance disabled

NVIDIA Open Model Licensecommercial_customSource verified

Specification

Model ID

qwen-image-flash

Family

qwen-image

Modality

Media generation

Parameters

20.4B

Weights

53.7 GB

Minimum VRAM

48 GB

Capabilities

text2image

Pipeline

QwenImagePipeline

Backend

diffusers

Source

Weights and provenance.

Repository

nvidia/Qwen-Image-Flash

Registry license

NVIDIA Open Model License

Access

Open — weights fetch without accepting additional terms.

The licence above is the registry's. The source repository either states nothing, states the catch-all “other”, or carries a licence link and base model that its own tag contradicts — a re-quantisation inherits the terms of the weights it derives from. The registry's licence is the one to rely on.

Serve it

# Pull the weights onto a node
tenzro model download qwen-image-flash

# Serve it
tenzro model serve qwen-image-flash

# Or query the registry entry over JSON-RPC
curl https://rpc.tenzro.xyz \
  -X POST -H "Content-Type: application/json" \
  -d '{"jsonrpc":"2.0","id":1,
       "method":"tenzro_getModel",
       "params":[{"model_id":"qwen-image-flash"}]}'

Same family

Qwen-Image 2512 (GGUF Q5_K_M)

20.4B

← All models