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