---
title: Qwen-Image-2.1-Turbo-GGUF
canonical_url: "https://www.modelscope.cn/models/AtomicChat/Qwen-Image-2.1-Turbo-GGUF"
md_url: "https://www.modelscope.cn/models/AtomicChat/Qwen-Image-2.1-Turbo-GGUF.md"
repository: AtomicChat/Qwen-Image-2.1-Turbo-GGUF
last_updated: 2026-10-28
license: other
pipeline_tag: text-to-image-synthesis
tasks:
- text-to-image-synthesis
base_model:
- Qwen/Qwen-Image-2.1-Turbo
base_model_relation: quantized
library_name:
- lora
- gguf
- pytorch
frameworks:
- pytorch
downloads: 1929
stars: 16
tags:
- gguf
- stable-diffusion.cpp
- qwen
- qwen-image
- text-to-image
- image-editing
- imatrix
- quantized
- atomic-chat
---
# Qwen-Image-2.1-Turbo-GGUF
> Qwen-Image-2.1-Turbo-GGUF - AtomicChat 在 ModelScope 开源的模型。How to Run Qwen-Image-2.1-Turbo Locally The 8-step Qwen-Image-2.1 as GGUF for stable-diffusion.cpp, built from the published BF16 weights with our own importance matrix. The renders and measurements…
AtomicChat/Qwen-Image-2.1-Turbo-GGUF 是 ModelScope 魔搭社区上的text-to-image-synthesis模型，采用 other 许可，基于 Qwen/Qwen-Image-2.1-Turbo 构建。
- **Repository**: AtomicChat/Qwen-Image-2.1-Turbo-GGUF
- **License**: other
- **Tasks**: text-to-image-synthesis
- **Base model**: Qwen/Qwen-Image-2.1-Turbo
- **Tags**: gguf, stable-diffusion.cpp, qwen, qwen-image, text-to-image, image-editing, imatrix, quantized, atomic-chat
- **Downloads**: 1929
- **Stars**: 16
- **Last updated**: 2026-10-28
Source: https://www.modelscope.cn/models/AtomicChat/Qwen-Image-2.1-Turbo-GGUF
---
# How to Run Qwen-Image-2.1-Turbo Locally
The 8-step Qwen-Image-2.1 as GGUF for stable-diffusion.cpp, built from the published BF16 weights with our own importance matrix. The renders and measurements behind this card are public.
- Generate images locally in Atomic Chat. It runs stable-diffusion.cpp, the engine these files were built and checked with.
- Turbo drifts from the original picture faster than you might expect at 4 bits and below. Our
AD-Q4_K stays 21% closer to the BF16 image than the plain Q4_K, for 150 MB more.
- Turbo needs its own 8-step schedule at CFG 1. The exact settings are in Running it.
- Looking for uncensored? The open Qwen-Image pipeline has no content filter. Qwen-Image-2.1-Turbo-Uncensored-GGUF removes the refusal direction from its text encoder. On images that changed nothing we could measure, and the card shows why.
[Qwen-Image-2.1-Turbo](https://huggingface.co/Qwen/Qwen-Image-2.1-Turbo) is Qwen's accelerated checkpoint
of Qwen-Image-2.1: the same 7B image generator, distilled to **8 denoising steps at CFG 1**, with its own
fixed sampling schedule. This repo has the denoiser as GGUF for
[stable-diffusion.cpp](https://github.com/leejet/stable-diffusion.cpp). The text encoder (Qwen3-VL-8B) and the
VAE are the same as in Qwen-Image-2.1, so the files you may already have for 2.1 work here.
## Pick a file
Each file renders the same 48 prompts × 2 seeds from the same starting noise as the BF16 weights. We compare every
image with the BF16 image of the same prompt and seed.
- `LPIPS` is a perceptual distance: lower is closer to the original picture, 0 is identical.
- `vs. new seed` puts it on a scale. 100% is how far the BF16 weights move when only the seed changes, which gives
an unrelated picture of the same prompt (LPIPS 0.499).
- `text (zh)` is the LPIPS on the eight prompts that put Chinese text into the image. Text breaks before
photographs do.
| File | Size on disk | LPIPS [95% CI] | vs. new seed | SSIM | PSNR | text (zh) |
|---|---:|---|---:|---:|---:|---:|
| `BF16` | 14.23 GB | 0 (identical) | 0% | 1.000 | — | 0 |
| `Q8_0` | 7.59 GB | 0.037 [0.030, 0.046] | 7% | 0.964 | 30.2 dB | 0.037 |
| `AD-Q6_K` | 6.71 GB | 0.044 [0.035, 0.055] | 9% | 0.956 | 29.6 dB | 0.052 |
| `AD-Q5_K` | 5.40 GB | 0.076 [0.064, 0.090] | 15% | 0.922 | 25.2 dB | 0.080 |
| **`AD-Q4_K`** | **4.20 GB** | **0.147 [0.128, 0.167]** | **29%** | **0.850** | **20.8 dB** | **0.166** |
| `AD-Q3_K` | 3.60 GB | 0.206 [0.182, 0.232] | 41% | 0.801 | 18.6 dB | 0.267 |
| `AD-Q2_K` | 2.55 GB | 0.359 [0.328, 0.389] | 72% | 0.671 | 14.7 dB | 0.421 |
- **`Q8_0`** is the closest to the original. Pick it if it fits.
- **`AD-Q6_K`** is 0.88 GB smaller than `Q8_0` and only slightly further from the original.
- **`AD-Q5_K`** keeps the composition. Details move.
- **`AD-Q4_K`** is the pick at 4 bits.
- **`AD-Q3_K`** draws the same scene with visible shifts in layout, faces and lettering.
- **`AD-Q2_K`** draws a noticeably different picture from the same seed. It still follows the prompt and spells
the text correctly in our spot checks. Use it only if nothing larger fits.
- The BF16 weights render deterministically here: two BF16 runs give identical images, so every number above
comes from quantization.
The same four prompts and seed, from left to right: BF16, `Q8_0`, `AD-Q4_K`, plain `Q4_K`, `AD-Q2_K`, plain `Q2_K`.
The plain files are the baseline, see [below](#how-these-compare-with-plain-ggufs).
### What `AD-` changes
`AD-` means Atomic Dynamic. The type is chosen per tensor instead of applied to every block, and the file is
quantized with an importance matrix from 32 Turbo renders that share no prompt with the evaluation set.
- The modulation shared by every block stays at Q8_0 (BF16 in `AD-Q6_K`). The plain files quantize it to the base
type, down to Q2_K.
- The timestep embedding, the final norm and the output projection stay in BF16.
- Attention is one step above the base type: in every block for Q6, Q5 and Q3, and in the first and last four
blocks for Q4 and Q2.
- In `AD-Q6_K`, `AD-Q5_K` and `AD-Q3_K`, the MLP output of the first and last eight blocks is one step up as well.
## How these compare with plain GGUFs
A plain GGUF is what `sd-cli -M convert --type` gives: every tensor at one type, no importance matrix. The first
Turbo GGUFs on the Hub, DogukanUrker's `Q4_K` and `Q8_0`, are exactly that. Their weights equal plain files we
built and measured the same way. They keep `gate_layer` and `proj` as two tensors, and those concatenate to our
`gate_up` exactly. Our `Q8_0` is the plain one too.
We measured the plain rungs as the baseline and do not ship them here:
| Plain file | Size on disk | LPIPS [95% CI] | vs. new seed | Our file at about that size |
|---|---:|---|---:|---|
| `Q6_K` | 5.88 GB | 0.072 [0.056, 0.090] | 14% | `AD-Q5_K`, 5.40 GB: 0.076 |
| `Q5_K` | 4.94 GB | 0.115 [0.098, 0.133] | 23% | `AD-Q5_K`, 5.40 GB: 0.076 |
| `Q4_K` | 4.05 GB | 0.187 [0.161, 0.214] | 37% | `AD-Q4_K`, 4.20 GB: 0.147 |
| `Q3_K` | 3.11 GB | 0.293 [0.267, 0.321] | 59% | `AD-Q3_K`, 3.60 GB: 0.206 |
| `Q2_K` | 2.39 GB | 0.475 [0.454, 0.496] | 95% | `AD-Q2_K`, 2.55 GB: 0.359 |
Paired over the 48 prompts, with a bootstrap interval on the difference in LPIPS:
| Comparison | Size | LPIPS difference [95% CI] | |
|---|---|---|---|
| `AD-Q4_K` against plain `Q4_K` | +150 MB | −0.039 [−0.056, −0.024] | 21% closer |
| `AD-Q3_K` against plain `Q3_K` | +490 MB | −0.087 [−0.105, −0.070] | 30% closer |
| `AD-Q2_K` against plain `Q2_K` | +160 MB | −0.117 [−0.141, −0.094] | 25% closer |
| `AD-Q5_K` against plain `Q6_K` | −480 MB | +0.005 [−0.008, +0.016] | the same within noise |
| `AD-Q6_K` against `Q8_0` | −880 MB | +0.007 [+0.002, +0.013] | `Q8_0` slightly closer |
At 4 bits we also separated the two levers at the exact size of plain `Q4_K`:
- The importance matrix alone makes the plain `Q4_K` 16% closer: −0.030 [−0.046, −0.015].
- The layout takes `AD-Q4_K` another 6% on top.
Plain `Q2_K` draws a different picture from the same seed, as far from the BF16 image as a new seed is.
## Running it
Turbo needs its own sampling schedule. Without `--sigmas`, stable-diffusion.cpp uses Qwen-Image-2.1's
default schedule, which the model was not distilled for, and the image comes out different.
```bash
sd-cli --diffusion-model Qwen-Image-2.1-Turbo-AD-Q4_K.gguf \
--vae qwen_image_2.1_vae_bf16.safetensors \
--llm Qwen3VL-8B-Instruct-Q8_0.gguf \
-p 'a neon sign that reads "OPEN LATE", rainy night' \
--steps 8 --cfg-scale 1.0 --sampling-method euler \
--sigmas 1.0,0.978453,0.95418,0.926626,0.89508,0.845148,0.704534,0.414568,0.0 \
-W 1024 -H 1024 --diffusion-fa -o out.png
```
- The schedule is `sample_sigmas` from the checkpoint's `model_index.json` plus the final `0.0`. The scheduler's
shift is 1.0, so the values are used as they are.
- Through the server API, pass the same list as `sample_params.custom_sigmas`.
- Use a stable-diffusion.cpp build from 6 October 2026 or newer (commit `c150a6b` fixed custom sigma lists).
- The VAE is `vae/qwen_image_2.1_vae_bf16.safetensors` from
[Comfy-Org/Qwen-Image-2.1](https://huggingface.co/Comfy-Org/Qwen-Image-2.1). Its tensors are identical to
Turbo's own VAE. The text encoder is any GGUF of
[Qwen3-VL-8B-Instruct](https://huggingface.co/Qwen/Qwen3-VL-8B-Instruct-GGUF). For editing, add its mmproj as
`--llm_vision` and the input image as `-r`.
- **The encoder's quantization moves the pictures too**, measured on the same 48 prompts:
- a Q8_0 encoder moves them by LPIPS 0.037 against the BF16 encoder;
- a plain Q4_K_M encoder by about 0.17, as much as our `AD-Q4_K` denoiser does.
Use a Q8_0 encoder if it fits. [Our encoder ladder](https://huggingface.co/AtomicChat/Qwen-Image-2.1-Turbo-Uncensored-GGUF)
has an `AD-Q4_K` at 5.29 GB that moves them by 0.087. The Q4_K_M number was measured on that (abliterated) build
of the encoder.
- Qwen recommends about 2 megapixels (2048×2048 for 1:1). Our measurements are at 1024×1024.
## How it was measured
- **Engine:** stable-diffusion.cpp at `36f1b1a` (upstream `0963357`) on an NVIDIA A100 80 GB.
- **Settings:** 1024×1024 with the settings in [Running it](#running-it), `--rng cpu`, seeds 42 and 43.
- **Prompts:** 48 evaluation prompts in six categories: photo, illustration, English text, Chinese text,
several objects with attributes, and transparent RGBA.
- **Held constant:** the text encoder and the VAE stayed in BF16 for every render, so the denoiser file was the
only thing that changed.
- **Not measured:** aesthetics or prompt adherence, editing with reference images, other step counts,
resolutions or samplers, and runtimes other than stable-diffusion.cpp.
- **In the [metrics repo](https://huggingface.co/datasets/AtomicChat/Qwen-Image-2.1-Turbo-GGUF-metrics):** every
render, the prompts, the importance matrix, the per-tensor layout of every file and every log.
## How these files were made
1. Qwen's diffusers shards (revision `d65dbc9`), checked against the Hub's sha256.
2. Written as one file in Comfy-Org's layout, the input stable-diffusion.cpp's rules expect. The only change is that
the MLP input is stored fused: `img_mlp.gate_up = cat(gate_layer, proj)`. That is a byte concatenation, so
nothing is rounded. `BF16` is byte-identical to the published checkpoint, tensor by tensor, and renders the
same image pixel for pixel.
3. Converted with `sd-cli -M convert` from
[stable-diffusion.cpp](https://github.com/AtomicBot-ai/stable-diffusion.cpp) at `36f1b1a`. The `AD-` files
add `--tensor-type-rules` and `--imat-in`, with the exact command for each file in the metrics repo.
## Changes
- **26.10.2026:** `Q8_0` re-uploaded. `sd-cli -M convert` had quantized its 64 one-dimensional QK-norm
weights to Q8_0 as well, and ComfyUI-GGUF cannot load quantized norms. They are F32 now; every other tensor
is byte-identical, and stable-diffusion.cpp renders the same image pixel for pixel. Thanks for the report
and the fix in [discussion #2](https://huggingface.co/AtomicChat/Qwen-Image-2.1-Turbo-GGUF/discussions/2).
