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
NE
Nemotron 3 Nano 30B A3B RotorQuant GGUF Q3 K M
Nemotron · majentik
Params31.6B
Context1024K
Smallest19.8 GB
ReasoningTool use
GE
gemma 4 E2B RotorQuant GGUF Q2 K
Gemma · majentik
Params4.65B
Context128K
Smallest3.0 GB
Vision
GE
gemma 4 26B A4B RotorQuant GGUF Q5 K M
Gemma · majentik
Params25.2B
Context256K
Smallest19.1 GB
Vision
NE
Nemotron 3 Super 120B A12B TurboQuant GGUF Q4 K M
Nemotron · majentik
Params121B
Context1024K
Q4_K_M86.1 GB
GGUF
QW
Qwen3 Embedding 0.6B GGUF Q4 K M
Qwen · majentik
Params596M
Context32K
Q4_K_M0.4 GB
EmbeddingReasoningTool use
GE
gemma 4 26B A4B RotorQuant GGUF IQ4 XS
Gemma · majentik
Params25.2B
Context256K
Smallest14.1 GB
Vision
GE
gemma 4 12B TurboQuant GGUF Q4 K M
Gemma · majentik
Params11.9B
Context256K
Q4_K_M7.4 GB
GGUF
QW
Qwen3 Embedding 4B GGUF Q5 K M
Qwen · majentik
Params4.02B
Context40K
Smallest2.9 GB
EmbeddingTool use
QW
Qwen3.5 27B RotorQuant GGUF Q3 K M
Qwen · majentik
Params26.9B
Context256K
Smallest13.3 GB
ReasoningTool use
MI
MiniCPM5 1B
MiniCPM · majentik
Params1.08B
Context128K
Q4_K_M0.7 GB
ReasoningTool use
NE
Nemotron Cascade 2 30B A3B TurboQuant GGUF Q4 K M
Nemotron · majentik
Params31.6B
Context1024K
Q4_K_M24.5 GB
ReasoningTool use
NE
Nemotron 3 Nano 30B A3B RotorQuant GGUF Q8 0
Nemotron · majentik
Params31.6B
Context1024K
Smallest33.6 GB
ReasoningTool use
NE
Nemotron 3 Nano 30B A3B RotorQuant GGUF IQ4 XS
Nemotron · majentik
Params31.6B
Context1024K
Smallest18.2 GB
ReasoningTool use
NE
Nemotron 3 Super 120B A12B TurboQuant GGUF Q2 K
Nemotron · majentik
Params121B
Context1024K
Smallest53.5 GB
GGUF
GE
gemma 4 E2B it RotorQuant GGUF Q3 K M
Gemma · majentik
Params4.65B
Context128K
Smallest3.2 GB
Vision
GE
gemma 4 E2B RotorQuant GGUF Q3 K M
Gemma · majentik
Params4.65B
Context128K
Smallest3.2 GB
Vision
NE
Nemotron 3 Nano 30B A3B TurboQuant GGUF Q4 K M
Nemotron · majentik
Params31.6B
Context1024K
Q4_K_M24.5 GB
ReasoningTool use
NO
nomic embed text v2 moe GGUF Q8 0
Nomic · majentik
Params475M
Context2K
Smallest0.5 GB
Embedding
GE
gemma 4 31B RotorQuant GGUF Q2 K
Gemma · majentik
Params30.7B
Context256K
Smallest11.9 GB
Vision
QW
Qwen3.5 27B RotorQuant GGUF IQ4 XS
Qwen · majentik
Params26.9B
Context256K
Smallest15.2 GB
ReasoningTool use
NO
nomic embed text v2 moe GGUF Q4 K M
Nomic · majentik
Params475M
Context2K
Q4_K_M0.4 GB
Embedding
QW
Qwen3 Embedding 8B GGUF Q4 K M
Qwen · majentik
Params7.57B
Context40K
Q4_K_M4.7 GB
EmbeddingTool use
NE
Nemotron 3 Nano 4B RotorQuant GGUF Q3 K M
Nemotron · majentik
Params3.97B
Context1024K
Smallest2.4 GB
ReasoningTool use
QW
Qwen3.5 27B RotorQuant GGUF Q2 K
Qwen · majentik
Params26.9B
Context256K
Smallest10.7 GB
ReasoningTool use
GE
gemma 4 E4B RotorQuant GGUF Q2 K
Gemma · majentik
Params7.52B
Context128K
Smallest4.4 GB
Vision
GE
gemma 4 E2B it RotorQuant GGUF Q2 K
Gemma · majentik
Params4.65B
Context128K
Smallest3.0 GB
Vision
NE
Nemotron 3 Nano Omni 30B A3B Reasoning TurboQuant GGUF Q3 K M
Nemotron · majentik
Params31.6B
Context1024K
Smallest19.8 GB
ReasoningTool useVision
NO
nomic embed text v2 moe GGUF Q5 K M
Nomic · majentik
Params475M
Context2K
Smallest0.4 GB
Embedding
NE
Nemotron Cascade 2 30B A3B TurboQuant GGUF Q3 K M
Nemotron · majentik
Params31.6B
Context1024K
Smallest19.8 GB
ReasoningTool use
NE
Nemotron 3 Super 120B A12B TurboQuant GGUF Q3 K M
Nemotron · majentik
Params121B
Context1024K
Smallest67.2 GB
GGUF

Keep browsing