Instructions to use ThirdMiddle/Qwen-Image-1.9 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ThirdMiddle/Qwen-Image-1.9 with Diffusers:

pip install -U diffusers transformers accelerate

import torch
from diffusers import DiffusionPipeline

# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("ThirdMiddle/Qwen-Image-1.9", dtype=torch.bfloat16, device_map="cuda")

prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]

llama-cpp-python

How to use ThirdMiddle/Qwen-Image-1.9 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="ThirdMiddle/Qwen-Image-1.9",
	filename="quantize/gguf/model-IQ4_XS.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use ThirdMiddle/Qwen-Image-1.9 with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf ThirdMiddle/Qwen-Image-1.9:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf ThirdMiddle/Qwen-Image-1.9:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf ThirdMiddle/Qwen-Image-1.9:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf ThirdMiddle/Qwen-Image-1.9:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf ThirdMiddle/Qwen-Image-1.9:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf ThirdMiddle/Qwen-Image-1.9:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf ThirdMiddle/Qwen-Image-1.9:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ThirdMiddle/Qwen-Image-1.9:Q4_K_M

Use Docker

docker model run hf.co/ThirdMiddle/Qwen-Image-1.9:Q4_K_M

LM Studio
Jan
Draw Things
DiffusionBee
Ollama
How to use ThirdMiddle/Qwen-Image-1.9 with Ollama:
```
ollama run hf.co/ThirdMiddle/Qwen-Image-1.9:Q4_K_M
```

Unsloth Studio new

How to use ThirdMiddle/Qwen-Image-1.9 with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for ThirdMiddle/Qwen-Image-1.9 to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for ThirdMiddle/Qwen-Image-1.9 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ThirdMiddle/Qwen-Image-1.9 to start chatting

Docker Model Runner
How to use ThirdMiddle/Qwen-Image-1.9 with Docker Model Runner:
```
docker model run hf.co/ThirdMiddle/Qwen-Image-1.9:Q4_K_M
```

Lemonade

How to use ThirdMiddle/Qwen-Image-1.9 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ThirdMiddle/Qwen-Image-1.9:Q4_K_M

Run and chat with the model

lemonade run user.Qwen-Image-1.9-Q4_K_M

List all available models

lemonade list

Qwen-Image-1.9

A merged, abliterated, and quantized derivative of the Qwen-Image 20B MMDiT family.

Run ID: prod-20260407 Created: 2026-04-07T18:59:37+00:00

Architecture

Property	Value
Base family	Qwen-Image (MMDiT 20B)
Text encoder	Qwen2.5-VL
VAE	RGB-VAE
RoPE	2D
Backbone parameters	~20B
License	Apache-2.0

Source Models

Alias	Model	Role	License
`qwen-image-2512`	Qwen/Qwen-Image-2512	foundation	Apache-2.0
`qwen-image-base`	Qwen/Qwen-Image	ancestry-base	Apache-2.0
`qwen-image-edit-2511`	Qwen/Qwen-Image-Edit-2511	edit-donor	Apache-2.0
`qwen-image-layered`	Qwen/Qwen-Image-Layered	layer-logic-donor	Apache-2.0

Research Method

1. Delta-Edit Merge

The edit capability is transferred to the foundation model via a controlled delta injection:

edit_delta = Qwen-Image-Edit-2511 − Qwen-Image (delta base)
merged     = Qwen-Image-2512 + 0.35 × edit_delta

Only MMDiT backbone tensors are blended. Text encoder, VAE, and RoPE components are passed through from the foundation checkpoint unchanged.

Strategy: slerp
Blend coefficient: 0.35
Foundation: Qwen/Qwen-Image-2512
Excluded subsystems: text_encoder, vae, rope

2. Abliteration (Refusal-Direction Removal)

Refusal-direction vectors are identified in the residual stream and projected out of target weight matrices using a norm-preserving orthogonal projection:

W′ = W − scale × (W @ r̂) ⊗ r̂    (norm-preserving variant)

Target layers: 18+ (attention o_proj + MLP down_proj)
Scale: 1.0
Mode: norm-preserving (preserves weight magnitude distribution)
Recipe: stage-3-abliteration.yaml

3. Quantization

Kind	Path
`quant_config`	`quant-config.json`

GGUF targets: Q4_K_M, IQ4_XS (with importance-matrix)
EXL2 target: 4.0 bpw
Runtime: vLLM-Omni (ROCm), ExLlamaV2

Hardware

GPU: AMD Instinct MI300X — 192 GB HBM3 VRAM
ROCm: 7.2.0
Precision: bf16 (merge + abliterate), quantized (deployment)

Usage

from diffusers import DiffusionPipeline
import torch

pipe = DiffusionPipeline.from_pretrained(
    "ThirdMiddle/Qwen-Image-1.9",
    torch_dtype=torch.bfloat16,
    trust_remote_code=True,
)
pipe = pipe.to("cuda")

image = pipe(
    "a photorealistic portrait of an astronaut on Mars at sunrise",
    num_inference_steps=30,
    guidance_scale=4.0,
).images[0]
image.save("output.png")

License

Apache-2.0 — inherited from all source models.

Downloads last month: 1,602

GGUF

Model size

8B params

Architecture

qwen2vl

Hardware compatibility

4-bit

16-bit

Model tree for ThirdMiddle/Qwen-Image-1.9

Base model

Qwen/Qwen-Image

Quantized

(25)

this model