Disty0
FLUX.2-klein-4B-SDNQ-4bit-dynamic
Z-Image-Turbo-SDNQ-uint4-svd-r32
t5-xxl
FLUX.2-dev-SDNQ-uint4-svd-r32
Qwen-Image-Edit-2509-SDNQ-uint4-svd-r32
4 bit (UINT4 with SVD rank 32) quantization of Qwen/Qwen-Image-Edit-2509 using SDNQ.
sotediffusion-wuerstchen3
sotediffusion-wuerstchen3-decoder
sotediffusion-v2
FLUX.1-dev-SDNQ-uint4-svd-r32
4 bit (UINT4 with SVD rank 32) quantization of black-forest-labs/FLUX.1-dev using SDNQ. | Quantization | Model Size | Visualization | | --- | --- | --- | | Original BF16 | 23.8 GB | | | SDNQ UINT4 | 6.8 GB | |
HunyuanImage3-SDNQ-uint4-svd-r32
GLM-Image-SDNQ-4bit-dynamic
LCM_SoteMix
FLUX.1-dev-qint8
FLUX.2-klein-9B-SDNQ-4bit-dynamic-svd-r32
Wan2.2-T2V-A14B-SDNQ-uint4-svd-r32
Florence-2-large-PromptGen-v2.0
Chroma1-HD-SDNQ-uint4-svd-r32
FLUX.1-schnell-SDNQ-uint4-svd-r32
4 bit (UINT4 with SVD rank 32) quantization of black-forest-labs/FLUX.1-schnell using SDNQ. | Quantization | Model Size | Visualization | | --- | --- | --- | | Original BF16 | 23.8 GB | | | SDNQ UINT4 | 6.8 GB | |
Qwen-Image-Lightning-SDNQ-uint4-svd-r32
Wan2.2-I2V-A14B-SDNQ-uint4-svd-r32
4 bit (UINT4 with SVD rank 32) quantization of Wan-AI/Wan2.2-I2V-A14B-Diffusers using SDNQ.
Florence-2-base-PromptGen-v1.5
Huggingface Transformers compatible version of: https://huggingface.co/MiaoshouAI/Florence-2-base-PromptGen-v1.5
NoobAI-XL-v1.1-SDNQ-uint4-svd-r128
Qwen3-VL-32B-Instruct-SDNQ-uint4-svd-r32
4 bit (UINT4 with SVD rank 32) quantization of Qwen/Qwen3-VL-32B-Instruct using SDNQ.
Qwen-Image-Edit-Lightning-SDNQ-uint4-svd-r32
4 bit (UINT4 with SVD rank 32) quantization of vladmandic/Qwen-Lightning-Edit using SDNQ.
Qwen-Image-SDNQ-uint4-svd-r32
FLUX.1-Kontext-dev-SDNQ-uint4-svd-r32
4 bit (UINT4 with SVD rank 32) quantization of black-forest-labs/FLUX.1-Kontext-dev using SDNQ. | Quantization | Model Size | Visualization | | --- | --- | --- | | Input Image | - | | | Original BF16 | 23.8 GB | | | SDNQ UINT4 | 6.8 GB | |
NoobAI-XL-Vpred-v1.0-SDNQ-uint4-svd-r128
FLUX.1-Krea-dev-SDNQ-uint4-svd-r32
aesthetic-shadow-v2
Reupload of `shadowlilac/aesthetic-shadow-v2` in FP16 dtype.
Qwen-Image-Edit-SDNQ-uint4-svd-r32
4 bit (UINT4 with SVD rank 32) quantization of Qwen/Qwen-Image-Edit using SDNQ.
ChronoEdit-14B-SDNQ-uint4-svd-r32
4 bit (UINT4 with SVD rank 32) quantization of nvidia/ChronoEdit-14B-Diffusers using SDNQ. | Quantization | Model Size | Visualization | | --- | --- | --- | | Input Image | - | | | Original BF16 | 28.6 GB | | | SDNQ UINT4 | 9.5 GB | |
sotediffusion-wuerstchen3-alpha3
sotediffusion-wuerstchen3-alpha1
Qwen-Image-2512-SDNQ-4bit-dynamic
Florence-2-base-PromptGen-v2.0
SoteMixV3
stable-diffusion-xl-base-1.0-fp16-vae
sote-diffusion-cascade-decoder_alpha0
sote-diffusion-cascade_pre-alpha0
Qwen-Image-2512-SDNQ-uint4-svd-r32
Florence-2-large-PromptGen-v1.5
sote-diffusion-cascade_alpha0
sd3_vae_anime_ft
sotediffusion-wuerstchen3-alpha1-decoder
SoteMixV2.2
SoteMix
sotediffusion-wuerstchen3-alpha3-decoder
sotediffusion-wuerstchen3-alpha2
SoteMixV2
Index-anisora-5B_RL-diffusers
FLUX.1-dev-qint4
sote-diffusion-cascade-decoder_pre-alpha0
sd3_randn_aura_vae
SoteMixV2.1
FLUX.1-dev-qint4_tf-qint8_te
openclip_g
clip_l
Index-anisora-5B-diffusers
Source file: https://huggingface.co/IndexTeam/Index-anisora/blob/main/5B/1000/mprank00modelstates.pt Soruce file sha256sum: `5ebdea887b5eda837aabcbf3ed9a344bd518e9b8114829a4b195daf289a6d775` Text Encoder and VAE are from THUDM/CogVideoX-5b-I2V