GGUF models by majentik

129 GGUF models quantized by majentik on Hugging Face. Sizes run from 475M to 284B parameters. The longest trained context is 1024K tokens.

Most downloadedNewestLargestLongest contextSmallest
GE
gemma 4 31B RotorQuant GGUF Q3 K M
Gemma · majentik
Params30.7B
Context256K
Smallest15.3 GB
Vision
GE
gemma 4 26B A4B it RotorQuant GGUF IQ4 XS
Gemma · majentik
Params25.2B
Context256K
Smallest14.1 GB
Vision
GE
gemma 4 26B A4B RotorQuant GGUF Q2 K
Gemma · majentik
Params25.2B
Context256K
Smallest10.6 GB
Vision
GP
gpt oss 20b RotorQuant GGUF Q3 K M
gpt-oss · majentik
Params20.9B
Context128K
Smallest12.9 GB
Tool use
GE
gemma 4 31B it RotorQuant GGUF Q3 K M
Gemma · majentik
Params30.7B
Context256K
Smallest15.3 GB
Vision
GP
gpt oss 20b RotorQuant GGUF Q5 K M
gpt-oss · majentik
Params20.9B
Context128K
Smallest16.9 GB
Tool use
GE
gemma 4 E4B RotorQuant GGUF IQ4 XS
Gemma · majentik
Params7.52B
Context128K
Smallest5.1 GB
Vision
GE
gemma 4 31B it RotorQuant GGUF Q5 K M
Gemma · majentik
Params30.7B
Context256K
Smallest21.8 GB
Vision
GE
gemma 4 31B it RotorQuant GGUF Q8 0
Gemma · majentik
Params30.7B
Context256K
Smallest32.6 GB
Vision
GE
gemma 4 12B RotorQuant GGUF Q3 K M
Gemma · majentik
Params11.9B
Context256K
Smallest6.1 GB
GGUF
QW
Qwen3.6 35B A3B RotorQuant GGUF Q5 K M
Qwen · majentik
Params34.7B
Context256K
Smallest24.7 GB
ReasoningTool useVision
GE
gemma 4 31B RotorQuant GGUF Q5 K M
Gemma · majentik
Params30.7B
Context256K
Smallest21.8 GB
Vision
GP
gpt oss 20b RotorQuant GGUF IQ4 XS
gpt-oss · majentik
Params20.9B
Context128K
Smallest12.2 GB
Tool use
QW
Qwen3 Embedding 4B GGUF Q8 0
Qwen · majentik
Params4.02B
Context40K
Smallest4.3 GB
EmbeddingTool use
NE
Nemotron 3 Nano Omni 30B A3B Reasoning TurboQuant GGUF IQ4 XS
Nemotron · majentik
Params31.6B
Context1024K
Smallest18.2 GB
ReasoningTool useVision
NE
Nemotron Cascade 2 30B A3B TurboQuant GGUF IQ4 XS
Nemotron · majentik
Params31.6B
Context1024K
Smallest18.2 GB
ReasoningTool use
NE
Nemotron 3 Nano Omni 30B A3B Reasoning RotorQuant GGUF Q2 K
Nemotron · majentik
Params31.6B
Context1024K
Smallest17.9 GB
ReasoningTool useVision
GE
gemma 4 26B A4B RotorQuant GGUF Q8 0
Gemma · majentik
Params25.2B
Context256K
Smallest26.9 GB
Vision
GE
gemma 4 E2B RotorQuant GGUF Q8 0
Gemma · majentik
Params4.65B
Context128K
Smallest5.0 GB
Vision
GE
gemma 4 12B TurboQuant GGUF Q8 0
Gemma · majentik
Params11.9B
Context256K
Smallest12.7 GB
GGUF
GE
gemma 4 E2B it RotorQuant GGUF IQ4 XS
Gemma · majentik
Params4.65B
Context128K
Smallest3.3 GB
Vision
GE
gemma 4 E2B RotorQuant GGUF Q5 K M
Gemma · majentik
Params4.65B
Context128K
Smallest3.6 GB
Vision
GE
gemma 4 31B it RotorQuant GGUF IQ4 XS
Gemma · majentik
Params30.7B
Context256K
Smallest16.9 GB
Vision
NE
Nemotron 3 Nano Omni 30B A3B Reasoning TurboQuant GGUF Q5 K M
Nemotron · majentik
Params31.6B
Context1024K
Smallest26.0 GB
ReasoningTool useVision
GP
gpt oss 20b RotorQuant GGUF Q8 0
gpt-oss · majentik
Params20.9B
Context128K
Smallest22.3 GB
Tool use
QW
Qwen3.6 35B A3B RotorQuant GGUF Q8 0
Qwen · majentik
Params34.7B
Context256K
Smallest36.9 GB
ReasoningTool useVision
QW
Qwen3.5 27B RotorQuant GGUF Q4 K M
Qwen · majentik
Params26.9B
Context256K
Q4_K_M16.5 GB
ReasoningTool use
GE
gemma 4 31B RotorQuant GGUF IQ4 XS
Gemma · majentik
Params30.7B
Context256K
Smallest16.9 GB
Vision
GE
gemma 4 12B TurboQuant GGUF IQ4 XS
Gemma · majentik
Params11.9B
Context256K
Smallest6.7 GB
GGUF
QW
Qwen3.6 35B A3B RotorQuant GGUF IQ4 XS
Qwen · majentik
Params34.7B
Context256K
Smallest18.9 GB
ReasoningTool useVision

Keep browsing