unsloth/Qwen-Image-2.1-Turbo-FP8
text-to-image model by unsloth
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
This is an FP8 / INT8 quantized version of Qwen-Image-2.1-Turbo, the 8-step distilled checkpoint of Qwen-Image-2.1. Built from Qwen/Qwen-Image-2.1-Turbo at revision d65dbc9a7e8f6b5479e33dee6030eaab2a906509 with the same recipe as unsloth/Qwen-Image-2.1-FP8: norms, modulation, timestep embeddings and (for INT8) txtin stay bf16, every other linear is quantized. Scores are LPIPS (AlexNet) against the bf16 Turbo transformer at the card's settings (8 steps, CFG 1, the shipped sigma schedule, 1024x1024), 8 prompts x 2 seeds, with the same bf16 text encoder in every run. Everything here is safetensors rather than a pickle, so loading runs no arbitrary code. Needs a diffusers main build with pipeline-configured sampling sigmas (PR #14950). Qwen-Image-2.1-Turbo is an accelerated checkpoint of Qwen-Image-2.1 for text-to-image generation and image editing with 8 denoising steps. It uses the same 7B visual generation architecture and loads directly with QwenImage21Pipeline in Diffusers. The checkpoint includes its recommended sampling schedule, so it is ready to use without…
Read the full model card ↗ · Preview checked 2026-11-01T14:24:48.706Z
Inside the original model card — Document outline
- Read our How to Run Qwen-Image-2.1 Guide!
- Samples
- Introduction
- Quick Start
- Installation
- Text-to-Image
- Image Editing
- Sampling
- Supported Aspect Ratios
- Showcase
- Portrait Photography
- Human Poses and Motion
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: other. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
unsloth/Qwen-Image-2.1-Turbo-FP8 is a text-to-image model repository published by unsloth on Hugging Face. The source reports the diffusers library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- text-to-image
- Library
- diffusers
- Recent downloads (30 days)
- 296,903
- Cumulative likes
- 24
- Hugging Face trending score
- 0
- Reported safetensors parameters
- 7,115,124,736
- Architecture
- Not reported
- License
- other
- Access
- Not gated by Hugging Face
- Created
- 2026-10-10T00:42:53.000Z
- Last modified
- 2026-10-16T11:32:50.000Z
Compatibility and lineage
Reported languages: en, zh
Reported base models: Qwen/Qwen-Image-2.1-Turbo
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-11-01T06:51:31.475Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.
Related models
stabilityai/stable-diffusion-xl-base-1.0
abenzerps/Qwen-Image-2.1-Uncensored-Quantized