Qwen-Image 2.1 GGUF & uncensored builds compared

Every popular Qwen-Image 2.1 repo on Hugging Face in one table: quantized GGUF and MLX files, full-precision weights and derived models, including abliterated and uncensored versions. Image models in GGUF format load in ComfyUI through a GGUF loader node. Check the memory column to see what fits your machine.

Updated 2026-11-19 Β· 24 repos with 1,000+ downloads in 30 days Β· 14 GGUF Β· 0 MLX Β· 10 other Β· 6 uncensored

GGUF builds

ModelQuantUncensoredLicenseDownloads (30 days)
Qwen-Image-2.1-Uncensored-Quantized
abenzerps
GGUF (several)YesCustom (other)2.5M
Qwen-Image-2.1-Turbo-GGUF
unsloth
GGUF (several)–Custom (other)1.8M
Qwen-Image-2.1-GGUF
unsloth
GGUF (several)–Custom (other)1.6M
Qwen-Image-2.1-Turbo-Uncensored-GGUF
AtomicChat
GGUF (several)YesApache 2.0614.5K
Qwen-Image-2.1-Uncensored-Omni-Quantized
chatrlabs
GGUF (several)YesCustom (other)268.5K
Qwen-Image-2.1-Turbo-Quantized
abenzerps
GGUF (several)–Custom (other)208.1K
Qwen-Image-2.1-Turbo-GGUF
AtomicChat
GGUF (several)–Custom (other)206.5K
Qwen-Image-2.1-viggle-turbo
Viggle
GGUF (several)–Custom (other)190.2K
Qwen-Image-2.1-Turbo-GGUF
DogukanUrker
GGUF (several)–Custom (other)172.6K
Qwen-Image-2.1-GGUF
leejet
GGUF (several)–Not stated150.9K
Qwen-Image-2.1-Uncensored-Abenzerps-GGUF
KasugaiSakura
GGUF (several)YesCustom (other)95.7K
Qwen-Image-2.1-viggle-4-steps-turbo-GGUF
Abiray
GGUF (several)–Custom (other)69.3K
Qwen-Image-2.1-GGUF
Abiray
GGUF (several)–Custom (other)62.7K
Qwen-Image-2.1-Uncensored-GGUF
0xSojalSec
GGUF (several)YesCustom (other)60.3K

Full-precision and other formats

ModelQuantUncensoredLicenseDownloads (30 days)
Qwen-Image-2.1
Comfy-Org
––Custom (other)9.5M
Qwen-Image-2.1-FP8
unsloth
FP8–Custom (other)839K
Qwen-Image-2.1
unsloth
16-bit–Custom (other)565.3K
Qwen-Image-2.1-Turbo-FP8
unsloth
FP8–Custom (other)369.7K
Qwen-Image-2.1
Qwen
16-bit–Custom (other)288.4K
Qwen-Image-2.1-Lightning
lightx2v
––Not stated279.9K
Noct-Q-Uncensored-Qwen-Image-2.1
Noctaluna
–YesCustom (other)247.8K
Qwen-Image-2.1-Turbo
Qwen
16-bit–Custom (other)33.5K
Qwen-Image-2.1-Anime-Fusal
MicksHF
––Custom (other)11.7K
Qwen-Image-2.1
taurusduan
––Custom (other)3.5K

How this list is built

Hugging Face repos whose name contains β€œqwen-image-2.1”, seen in the last 30 days with at least 1,000 downloads in the last 30 days, sorted by downloads. Size comes from Hugging Face metadata, or from the repo name when the metadata has none. Memory is an estimate: parameters Γ— bytes per weight (about 0.5 for a 4-bit build, 2 for 16-bit) plus 20% headroom; long contexts need more. β€œGGUF (several)” means the repo offers several quant files.

Qwen3.8 27B builds β†’ Β· Qwen3.8 Flash Next builds β†’ Β· All uncensored models by memory β†’ Β· Find a model for your hardware β†’