GGUF models by realrebelai
37 GGUF models quantized by realrebelai on Hugging Face. Sizes run from 2.46B to 35B parameters.
MI
MiniMax H3 GGUFs
Minimax · realrebelai
Params33.1B
Context—
Q4_K_M14.6 GB
KR
KREA 2 GGUFs
Krea · realrebelai
Params12.9B
Context—
Q4_K_M7.2 GB
SC
SCAIL 2
Scail · realrebelai
Params16.4B
Context—
Q4_K_M10.9 GB
WA
Wan Animate 2 GGUFs
Wan · realrebelai
Params16.4B
Context—
Q4_K_M11.3 GB
LT
LTX 2.5 GGUFs
Ltx · realrebelai
Params21B
Context—
Q4_K_M15.1 GB
FL
FLUX 3 Image Klein GGUFs
Flux · realrebelai
Params5.54B
Context—
Q4_K_M3.4 GB
MO
MOSS Image GGUFs
Moss · realrebelai
Params5.08B
Context—
Q4_K_M3.7 GB
QW
Qwen Image 2.1 GGUFs
Qwen · realrebelai
Params7.12B
Context—
Smallest4.1 GB
FA
FastH3 V2 GGUFs
Fastvideo · realrebelai
Params35B
Context—
Q4_K_M14.6 GB
MI
Ming Image GGUFs
Ming · realrebelai
Params6.15B
Context—
Q4_K_M5.9 GB
FA
FastH3 Omni GGUFs
Fastvideo · realrebelai
Params22.1B
Context—
Q4_K_M13.8 GB
LL
LLaDa Image Turbo ComfyUI
Llada · realrebelai
Params16.3B
Context—
Q4_K_M9.2 GB
KA
Kandinsky 6.0 Pro 5s GGUFs
Kandinsky · realrebelai
Params—
Context—
Smallest20.4 GB
SE
SenseNova U1.5 8B GGUFs
Sensenova · realrebelai
Params17.5B
Context—
Smallest9.3 GB
FI
Fibo 2.0 GGUFs
Fibo · realrebelai
Params8.23B
Context—
Smallest6.6 GB
QW
Viggle Qwen Image 2.1 Turbo GGUFs
Qwen · realrebelai
Params7.12B
Context—
Q4_K_M5.6 GB
WA
Wan Dancer GGUFs
Wan · realrebelai
Params17.2B
Context—
Q4_K_M12.5 GB
KR
Krea R Turbo
Krea · realrebelai
Params12.8B
Context—
Q4_K_M7.7 GB
QW
Qwen Image 2.1 Turbo GGUFs
Qwen · realrebelai
Params7.12B
Context—
Smallest3.3 GB
LI
LingBot 30B 3B GGUF ComfyUI
Lingbot · realrebelai
Params30B
Context—
Q4_K_M17.0 GB
BO
Boogu Image Turbo GGUFs
Boogu · realrebelai
Params10.3B
Context—
Smallest6.8 GB
JO
JoyAI Echo
Joyai · realrebelai
Params12.2B
Context—
Q4_K_M15.7 GB
LL
LLaDa Image ComfyUI
Llada · realrebelai
Params16.3B
Context—
Q4_K_M9.2 GB
IR
iris 3b GGUFs
Iris · realrebelai
Params3B
Context—
Smallest1.3 GB
QW
Qwen Image Flash
Qwen · realrebelai
Params20.4B
Context—
Q4_K_M11.7 GB
BO
Boogu Image Edit GGUFs
Boogu · realrebelai
Params10.3B
Context—
Smallest6.8 GB
FA
FastH3 GGUFs
Fastvideo · realrebelai
Params35B
Context—
Q4_K_M19.8 GB
MI
MiniMax Music 3 GGUFs
Minimax · realrebelai
Params2.46B
Context—
Q4_K_M1.5 GB
BO
Boogu Image Base GGUFs
Boogu · realrebelai
Params10.3B
Context—
Smallest6.8 GB
LI
LingBot World V2 ComfyUI
Lingbot · realrebelai
Params18.5B
Context—
Q4_K_M12.1 GB
About realrebelai on Hugging Face
realrebelai has published 37 GGUF models that ggufmodels.com tracks, across families such as Qwen, Boogu and Krea. The most downloaded are MiniMax H3 GGUFs, KREA 2 GGUFs and SCAIL 2.
The quants realrebelai publishes most often are Q4_K_M (25), Q8_0 (23), Q6_K (23) and Q5_K_M (21). Their Q4_K_M files range from 1.5 to 19.9 GB. Parameter counts run from 2.46B to 35B.
Frequently asked questions
What GGUF models has realrebelai published?
37 models are listed here, mainly from the Qwen, Boogu and Krea families. The most downloaded is MiniMax H3 GGUFs.
Which quants does realrebelai publish?
The most common are Q4_K_M (25 models), Q8_0 (23 models), Q6_K (23 models) and Q5_K_M (21 models).