Qwen · Qwen-Image

Qwen-Image 2.1 Turbo

Verified by Badgr · Run

Qwen-Image 2.1 Turbo is a 7.1B image-generation model available through supported Badgr execution routes.

Last validated or meaningfully updated: 2026-10-10

Serve Qwen-Image 2.1 Turbo nowGet help running this

✓ Verified by Badgr · Diffusers · Run

Last verified 2026-10-10

badgr run --image vllm/vllm-openai:v0.30.0 --gpu auto --min-vram 40 --funding paid --max-cost 3 --max-runtime 40 --artifacts /workspace/out/fox.png --cmd 'pip install diffusers (main) ... QwenImage21Pipeline.from_pretrained("Qwen/Qwen-Image-2.1-Turbo", dtype=torch.bfloat16) ... num_inference_steps=8'
GPU
NVIDIA RTX A6000Reported by the provider, not confirmed inside the container
Command runtime
96s
Deployment
dep-2c65812dc7
  • ✓ Workload container started
  • ✓ Command exited with code 0
  • ✓ A 1024x1024 image was generated in 30.6 s (8 steps, model CPU offload)
  • ✓ The output file was written (1,518,410 bytes)
  • ✓ Teardown completed

The image was written inside the job and its size and file were checked there. Badgr did not return it through --artifacts for this job (badgr artifacts reported none), so no copy is published here. Needs diffusers from its main branch. The command is abridged.

Raw evidence
deployment=dep-2c65812dc7 status=succeeded user_command_exit=0
gpu NVIDIA RTX A6000 | load 23s | generate 30.6s | size (1024, 1024)
-rw-r--r-- 1 root root 1518410 fox.png

Run from Badgr's local development environment. Documents that this job works end-to-end for this model.

Availability

Not yet Badgr AI API

Not currently validated

✓ Dedicated endpoint

Available through Badgr

✓ Custom GPU deployment

Available through Badgr

Deployment profile

Architecture
QwenImage21Pipeline
Licence
Other
Minimum VRAM
~19GB
Context
Task dependent

Recommended: RTX 4090 24GB. VRAM is an estimate and increases with context, cache, concurrency, and runtime overhead.

Model identity

Base model
Qwen/Qwen-Image-2.1
Updated
2 days ago
HuggingFace revision
d65dbc9a7e

Popularity and trust

Downloads (last month)

2.1K

Likes

468

Spaces using this model

12

Files and formats

Weight formats

Safetensors

Repository files

32

Chat template

Available

GPU deployment scenarios

Estimated from parameter count and quantisation. Will switch to “Verified by Badgr” once a real run backs a tier.

Testing

RTX 4090 24GB

Short context, low concurrency

Small production

L40S 48GB

8K context, 1-4 concurrent requests

Higher throughput

A100 80GB

32K context, continuous batching

Large production

RTX 4090 24GB

Higher concurrency

Estimated — multimodal inputs, long context, and concurrency all increase real VRAM use beyond this estimate.

Also runs well on L40S 48GB, A100 40GB. Available in United States, Europe.

Serving compatibility

RuntimeStatusNotes
vLLMEstimatedUsed for Badgr dedicated endpoints
TransformersUnknownBasic fallback
llama.cppRequires GGUF conversionNo GGUF weights found in repo
SGLangUnknownNot evaluated
OllamaUnknownNot evaluated
DiffusersVerified for RunConfirmed by a real badgr run job (deployment dep-2c65812dc7); serving is not verified
PyTorchUnknownNot evaluated
TensorRT-LLMUnknownConversion may be required
TGIUnknownNot evaluated

Ready-to-run Badgr configurations

Quick test

badgr serve Qwen/Qwen-Image-2.1-Turbo --max-cost 2

Validated dedicated endpoint command

badgr serve Qwen/Qwen-Image-2.1-Turbo --gpu RTX 4090 --max-cost 10

Advanced configuration (defaults to automatic)

  • Runtime
  • Quantisation
  • GPU and GPU count
  • Context length
  • Maximum concurrency
  • Region
  • Maximum hourly spend
  • Persistent or capped runtime

Estimated pricing

Provider estimate: cold start

2–5 min

Provider estimate: endpoint cost

$0.23 – $0.45/hr

Idle cost

$0 when stopped

Per-token throughput cost is not shown here: Badgr has not benchmarked this model yet, and this page does not display figures it cannot back with real data.

Recommended Badgr routes

RTX 4090 24GB · United States

Available

from $0.23/hr

24GB VRAM/GPU16GB RAM1422.9GB storage0.02Gbps networkCUDA 13.2

Best for

ComfyUI, Batch Inference, Qwen 2.5 7B Instruct

Startup: 2–5 min

Reliability: Standard

Last checked: just now

Check live route
View details →

RTX 4090 24GB · United States

Available

from $0.43/hr

2x GPU24GB VRAM/GPUSame host8 vCPU31.3GB RAM683GB storage0.81Gbps networkCUDA 13.2

Best for

ComfyUI, Batch Inference, Qwen 2.5 7B Instruct

Startup: 2–5 min

Reliability: Standard

Last checked: just now

Check live route
View details →

RTX 4090 24GB · United States

Available

from $0.44/hr

24GB VRAM/GPU

Best for

ComfyUI, Batch Inference, Qwen 2.5 7B Instruct

Startup: 2–5 min

Reliability: Standard

Last checked: just now

Check live route
View details →

RTX 4090 24GB · Europe

Estimated

starting from $0.45/hr

Badgr estimated starting price

Best for

ComfyUI, Batch Inference, Qwen 2.5 7B Instruct

Startup: 2–5 min

Reliability: Standard

Last checked: Live marketplace price not available yet

Check live route
View details →

RTX 4090 24GB · Europe

Estimated

starting from $0.45/hr

Badgr estimated starting price

Best for

ComfyUI, Batch Inference, Qwen 2.5 7B Instruct

Startup: 2–5 min

Reliability: Standard

Last checked: Live marketplace price not available yet

Check live route
View details →

RTX 4090 24GB · Europe

Estimated

starting from $0.45/hr

Badgr estimated starting price

Best for

ComfyUI, Batch Inference, Qwen 2.5 7B Instruct

Startup: 2–5 min

Reliability: Standard

Last checked: Live marketplace price not available yet

Check live route
View details →

Known limitations

  • Memory use increases with context length and concurrency.

Related troubleshooting