GGUF models by mradermacher

71763 GGUF models quantized by mradermacher on Hugging Face. Sizes run from 2M to 673B parameters. The longest trained context is 10742K tokens.

Most downloadedNewestLargestLongest contextSmallest
OR
Ornith 1.5 9B Uncensored
Ornith · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
Vision
CY
Cyber Ornith 1.5 9B OBLITERATED
Cyber · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
CodingReasoningTool use
QW
Qwen3 VL 8B Instruct Abliterated
Qwen · mradermacher
Params8.19B
Context256K
Q4_K_M5.0 GB
Vision
SI
Simplicio 27B
Simplicio · mradermacher
Params27.3B
Context256K
Q4_K_M16.8 GB
CodingVision
AD
AdaVaR 3B
Adavar · mradermacher
Params3.09B
Context125K
Q4_K_M1.9 GB
Vision
QW
Qwen3.8 27B Fable 5 Coding Distilled
Qwen · mradermacher
Params27.3B
Context256K
Q4_K_M16.8 GB
ReasoningVision
QW
Qwen3.5 9B Kimi K3 Distilled
Qwen · mradermacher
Params9.2B
Context256K
Q4_K_M5.8 GB
ReasoningVision
B1
B1 9B
mradermacher
Params9.2B
Context256K
Q4_K_M5.8 GB
ReasoningTool useVision
HE
Hemmingway 1
Hemmingway · mradermacher
Params27.3B
Context256K
Q4_K_M16.8 GB
ReasoningTool use
QW
Huihui Qwen3.5 9B Abliterated
Qwen · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
ReasoningTool useVision
QW
Qwen3.8 Flash Next Uncensored i1
Qwen · mradermacher
Params177B
Context—
Smallest0.6 GB
ReasoningTool useVision
QW
Huihui Qwen3.8 Flash Next abliterated i1
Qwen · mradermacher
Params177B
Context—
Smallest0.6 GB
GGUF
GE
Gemma 4 26B A4B It Ultra Uncensored Heretic
Gemma · mradermacher
Params25.2B
Context256K
Q4_K_M16.8 GB
GGUF
QW
Huihui Qwen3.6 35B A3B Abliterated
Qwen · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
Vision
QW
Huihui Qwen3 Coder 30B A3B Instruct Abliterated
Qwen · mradermacher
Params30.5B
Context256K
Q4_K_M18.6 GB
Coding
QW
Huihui Qwen3.8 Flash Next Abliterated
Qwen · mradermacher
Params177B
Context256K
Smallest80.4 GB
Vision
LI
LING 3.0 FLASH ABLITERATED
Ling · mradermacher
Params127B
Context256K
Q4_K_M77.0 GB
Reasoning
QW
Huihui Qwen3.5 4B Abliterated
Qwen · mradermacher
Params4.21B
Context256K
Q4_K_M2.7 GB
ReasoningTool useVision
QW
Huihui Qwen3 14B Abliterated v2
Qwen · mradermacher
Params14.8B
Context40K
Q4_K_M9.0 GB
GGUF
QW
Huihui Qwen3 8B Abliterated v2
Qwen · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
GGUF
QW
Qwen3.8 Flash Next Uncensored
Qwen · mradermacher
Params177B
Context256K
Smallest80.4 GB
ReasoningTool useVision
LL
Llama3.3 8B Instruct Thinking Heretic Uncensored Claude 4.5 Opus High Reasoning
Llama · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
ReasoningRoleplay
QW
Qwen3.8 14B Instruct Turbo
Qwen · mradermacher
Params14.7B
Context256K
Q4_K_M9.2 GB
ReasoningTool use
QW
Qwen3.8 9B Heretic Uncensored
Qwen · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
ReasoningTool useVision
QW
Qwen 3.8 27B Uncensored
Qwen · mradermacher
Params27.3B
Context256K
Q4_K_M16.8 GB
Vision
QW
Huihui Qwen3 Coder Next Abliterated
Qwen · mradermacher
Params79.7B
Context256K
Q4_K_M48.5 GB
Coding
TR
Translategemma 12b It
Translategemma · mradermacher
Params11.8B
Context128K
Q4_K_M7.3 GB
Vision
QW
Qwen2.5 VL 7B Instruct
Qwen · mradermacher
Params7.62B
Context125K
Q4_K_M4.7 GB
Vision
QW
Huihui Qwen3 Coder 30B A3B Instruct Abliterated
Qwen · mradermacher
Params30.5B
Context256K
Q4_K_M18.6 GB
Coding
QW
Qwen2.5 VL 7B Instruct Abliterated
Qwen · mradermacher
Params7.62B
Context125K
Q4_K_M4.7 GB
Vision

About mradermacher on Hugging Face

mradermacher has published 71,763 GGUF models that ggufmodels.com tracks, across families such as Qwen, Llama and Gemma. The most downloaded are Ornith 1.5 9B Uncensored, Cyber Ornith 1.5 9B OBLITERATED and Qwen3 VL 8B Instruct Abliterated.

The quants mradermacher publishes most often are Q2_K (71469), Q3_K_S (71140), Q3_K_M (71033) and Q3_K_L (70967). Their Q4_K_M files range from 0.0 to 405.8 GB. Parameter counts run from 2M to 673B, and the longest trained context window is 10742K tokens.

Frequently asked questions

What GGUF models has mradermacher published?

71,763 models are listed here, mainly from the Qwen, Llama and Gemma families. The most downloaded is Ornith 1.5 9B Uncensored.

Which quants does mradermacher publish?

The most common are Q2_K (71469 models), Q3_K_S (71140 models), Q3_K_M (71033 models) and Q3_K_L (70967 models).

Keep browsing