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
GP
gpt oss 20b RotorQuant GGUF Q2 K
gpt-oss · majentik
Params20.9B
Context128K
Smallest12.1 GB
Tool use
NE
Nemotron 3 Nano Omni 30B A3B Reasoning TurboQuant GGUF Q4 K M
Nemotron · majentik
Params31.6B
Context1024K
Q4_K_M24.5 GB
ReasoningTool useVision
GE
gemma 4 E4B RotorQuant GGUF Q5 K M
Gemma · majentik
Params7.52B
Context128K
Smallest5.8 GB
Vision
QW
Qwen3 Embedding 8B GGUF Q5 K M
Qwen · majentik
Params7.57B
Context40K
Smallest5.4 GB
EmbeddingTool use
GE
gemma 4 E2B it RotorQuant GGUF Q5 K M
Gemma · majentik
Params4.65B
Context128K
Smallest3.6 GB
Vision
QW
Qwen3 Embedding 8B GGUF IQ4 XS
Qwen · majentik
Params7.57B
Context40K
Smallest4.3 GB
EmbeddingTool use
QW
Qwen3.5 27B RotorQuant GGUF Q8 0
Qwen · majentik
Params26.9B
Context256K
Smallest28.6 GB
ReasoningTool use
NE
Nemotron 3 Nano Omni 30B A3B Reasoning TurboQuant GGUF Q8 0
Nemotron · majentik
Params31.6B
Context1024K
Smallest33.6 GB
ReasoningTool useVision
QW
Qwen3 Embedding 8B GGUF Q8 0
Qwen · majentik
Params7.57B
Context40K
Smallest8.0 GB
EmbeddingTool use
QW
Qwen3.5 27B RotorQuant GGUF Q5 K M
Qwen · majentik
Params26.9B
Context256K
Smallest19.2 GB
ReasoningTool use
MI
MiniCPM5 1B Base
MiniCPM · majentik
Params1.08B
Context128K
Smallest0.8 GB
ReasoningTool use
MI
MiniCPM5 1B Base
MiniCPM · majentik
Params1.08B
Context128K
Smallest0.6 GB
ReasoningTool use
NE
Nemotron 3 Super 120B A12B TurboQuant GGUF Q8 0
Nemotron · majentik
Params121B
Context1024K
Smallest128.5 GB
GGUF
NE
Nemotron Cascade 2 30B A3B RotorQuant GGUF Q8 0
Nemotron · majentik
Params31.6B
Context1024K
Smallest33.6 GB
ReasoningTool use
GE
gemma 4 12B it RotorQuant GGUF Q4 K M
Gemma · majentik
Params11.9B
Context256K
Q4_K_M7.4 GB
ReasoningTool use
NE
Nemotron 3 Nano 30B A3B RotorQuant GGUF Q5 K M
Nemotron · majentik
Params31.6B
Context1024K
Smallest26.0 GB
ReasoningTool use
HA
harrier oss v1 0.6b GGUF Q4 K M
Harrier · majentik
Params596M
Context32K
Q4_K_M0.4 GB
EmbeddingReasoningTool use
NE
Nemotron 3 Super 120B A12B RotorQuant GGUF Q6 K
Nemotron · majentik
Params121B
Context1024K
Smallest112.9 GB
GGUF
NE
Nemotron 3 Super 120B A12B TurboQuant GGUF Q5 K M
Nemotron · majentik
Params121B
Context1024K
Smallest95.7 GB
GGUF
NE
Nemotron 3 Nano 30B A3B RotorQuant GGUF Q2 K
Nemotron · majentik
Params31.6B
Context1024K
Smallest17.9 GB
ReasoningTool use
NO
nomic embed text v2 moe GGUF IQ4 XS
Nomic · majentik
Params475M
Context2K
Smallest0.3 GB
Embedding
NE
Nemotron 3 Nano 4B RotorQuant GGUF Q2 K
Nemotron · majentik
Params3.97B
Context1024K
Smallest2.2 GB
ReasoningTool use
GE
gemma 4 12B it TurboQuant GGUF Q8 0
Gemma · majentik
Params11.9B
Context256K
Smallest12.7 GB
ReasoningTool use
QW
Qwen3 Embedding 4B GGUF IQ4 XS
Qwen · majentik
Params4.02B
Context40K
Smallest2.3 GB
EmbeddingTool use
HA
harrier oss v1 0.6b GGUF Q8 0
Harrier · majentik
Params596M
Context32K
Smallest0.6 GB
EmbeddingReasoningTool use
QW
Qwen3 Embedding 0.6B GGUF Q5 K M
Qwen · majentik
Params596M
Context32K
Smallest0.4 GB
EmbeddingReasoningTool use
MI
MiniCPM5 1B Base
MiniCPM · majentik
Params1.08B
Context128K
Smallest0.6 GB
ReasoningTool use
NE
Nemotron Cascade 2 30B A3B TurboQuant GGUF Q5 K M
Nemotron · majentik
Params31.6B
Context1024K
Smallest26.0 GB
ReasoningTool use
MI
MiniCPM5 1B
MiniCPM · majentik
Params1.08B
Context128K
Smallest0.6 GB
ReasoningTool use
MI
MiniCPM5 1B
MiniCPM · majentik
Params1.08B
Context128K
Smallest0.6 GB
ReasoningTool use

Keep browsing