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

Source license

other

Access

Open — weights fetch without accepting additional terms.

The registry records this model as NVIDIA Open Model License while the source repository states other. Both are shown here rather than one being preferred. Treat the stricter of the two as binding until the discrepancy is resolved upstream.

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