GGUF models by Otakadelic

101 GGUF models quantized by Otakadelic on Hugging Face. Sizes run from 1B to 31.4B parameters. The longest trained context is 128K tokens.

Most downloadedNewestLargestLongest contextSmallest
GE
Gemma 3 12b It Abliterated
Gemma · Otakadelic
Params11.8B
Context128K
Q4_K_M7.3 GB
Vision
GE
Gemma 3 1b It Abliterated
Gemma · Otakadelic
Params1B
Context32K
Q4_K_M0.8 GB
GGUF
ME
Mergekit Model_Stock Prczfmj
Mergekit · Otakadelic
Params27B
Context128K
Q4_K_M16.5 GB
GGUF
GE
Gemma 3 4b It Abliterated
Gemma · Otakadelic
Params3.88B
Context128K
Smallest3.2 GB
Vision
GE
Gemma 3 1b It Abliterated
Gemma · Otakadelic
Params1B
Context32K
Smallest1.0 GB
GGUF
QW
Qwen3 14B Claude 4.5 Opus High Reasoning Distill
Qwen · Otakadelic
Params14.8B
Context40K
Smallest12.1 GB
ReasoningTool use
PH
phi 4 abliterated Orion 18B Q4 K M
Phi · Otakadelic
Params18.1B
Context16K
Q4_K_M11.1 GB
GGUF
GE
Gemma 3 12b It Abliterated
Gemma · Otakadelic
Params11.8B
Context128K
Smallest9.7 GB
Vision
GE
Gemma 3 4b It Abliterated
Gemma · Otakadelic
Params3.88B
Context128K
Q4_K_M2.5 GB
Vision
GE
Gemma 3 4b It Abliterated
Gemma · Otakadelic
Params3.88B
Context128K
Smallest4.1 GB
Vision
GE
Gemma 3 12b It Abliterated
Gemma · Otakadelic
Params11.8B
Context128K
Smallest12.5 GB
Vision
VE
MN VelvetCafe RP 12B
Velvetcafe · Otakadelic
Params12.2B
Context128K
Smallest10.1 GB
Roleplay
LL
Meta Llama 3.1 8B Instruct Abliterated
Llama · Otakadelic
Params8.03B
Context128K
Smallest6.6 GB
Tool use
GE
Gemma 3 12b It v3 Merged
Gemma · Otakadelic
Params11.8B
Context128K
Q4_K_M7.3 GB
GGUF
GE
28_05_2025_Test2_LazyMergekit_gemma 3 12B
Gemma · Otakadelic
Params11.8B
Context128K
Q4_K_M7.3 GB
GGUF
GE
MT Gen6 gemma 2 9B Q4 K M
Gemma · Otakadelic
Params9.24B
Context8K
Q4_K_M5.8 GB
GGUF
GE
MT2 Gen2_gemma 3 12B
Gemma · Otakadelic
Params11.8B
Context128K
Q4_K_M7.3 GB
Vision
GE
MT Merge8 gemma 2 9B
Gemma · Otakadelic
Params9.24B
Context8K
Q4_K_M5.8 GB
GGUF
GE
MT3 Gen10 gemma 2 9B Q4 K M
Gemma · Otakadelic
Params9.24B
Context8K
Q4_K_M5.8 GB
GGUF
GE
MT3 Gen10 gemma 2 9B Q8 0
Gemma · Otakadelic
Params9.24B
Context8K
Smallest9.8 GB
GGUF
GE
MTM Merge1 gemma 2 9B Q4 K M
Gemma · Otakadelic
Params9.24B
Context8K
Q4_K_M5.8 GB
GGUF
GE
MT3 Gen2_gemma 3 12B
Gemma · Otakadelic
Params11.8B
Context128K
Smallest12.5 GB
Vision
GE
MT1 Gen8 gemma 2 9B
Gemma · Otakadelic
Params9.24B
Context8K
Smallest6.6 GB
GGUF
GE
MT2 Gen6 gemma 2 9B Q8 0
Gemma · Otakadelic
Params9.24B
Context8K
Smallest9.8 GB
GGUF
GE
MT3 Gen2_gemma 3 12B
Gemma · Otakadelic
Params11.8B
Context128K
Q4_K_M7.3 GB
Vision
GE
MT1 Gen2_gemma 3 12B
Gemma · Otakadelic
Params11.8B
Context128K
Q4_K_M7.3 GB
GGUF
GE
MT2 Gen6 gemma 2 9B Q4 K M
Gemma · Otakadelic
Params9.24B
Context8K
Q4_K_M5.8 GB
GGUF
PH
phi 4 abliterated Orion 18B Q8 0
Phi · Otakadelic
Params18.1B
Context16K
Smallest19.2 GB
GGUF
GE
MT3 Gen6 gemma 2 9B Q4 K M
Gemma · Otakadelic
Params9.24B
Context8K
Q4_K_M5.8 GB
GGUF
GE
MTMMe Merge gemma 2 9B NuSLERP w0.7 0.3 Q4 K M
Gemma · Otakadelic
Params9.24B
Context8K
Q4_K_M5.8 GB
GGUF

About Otakadelic on Hugging Face

Otakadelic has published 101 GGUF models that ggufmodels.com tracks, across families such as Gemma, Phi and Mergekit. The most downloaded are Gemma 3 12b It Abliterated, Gemma 3 1b It Abliterated and Mergekit Model_Stock Prczfmj.

The quants Otakadelic publishes most often are Q4_K_M (44), Q8_0 (40), Q6_K (10) and Q5_K_M (9). Their Q4_K_M files range from 0.8 to 19.0 GB. Parameter counts run from 1B to 31.4B, and the longest trained context window is 128K tokens.

Frequently asked questions

What GGUF models has Otakadelic published?

101 models are listed here, mainly from the Gemma, Phi and Mergekit families. The most downloaded is Gemma 3 12b It Abliterated.

Which quants does Otakadelic publish?

The most common are Q4_K_M (44 models), Q8_0 (40 models), Q6_K (10 models) and Q5_K_M (9 models).

Keep browsing