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
HA
harrier oss v1 0.6b GGUF Q5 K M
Harrier · majentik
Params596M
Context32K
Smallest0.4 GB
EmbeddingReasoningTool use
NE
Nemotron 3 Nano 4B RotorQuant GGUF IQ4 XS
Nemotron · majentik
Params3.97B
Context1024K
Smallest2.4 GB
ReasoningTool use
QW
Qwen3 Embedding 0.6B GGUF IQ4 XS
Qwen · majentik
Params596M
Context32K
Smallest0.4 GB
EmbeddingReasoningTool use
HA
harrier oss v1 0.6b GGUF IQ4 XS
Harrier · majentik
Params596M
Context32K
Smallest0.4 GB
EmbeddingReasoningTool use
MI
MiniCPM5 1B
MiniCPM · majentik
Params1.08B
Context128K
Smallest1.2 GB
ReasoningTool use
MI
MiniCPM5 1B Base
MiniCPM · majentik
Params1.08B
Context128K
Q4_K_M0.7 GB
ReasoningTool use
MI
MiniCPM5 1B
MiniCPM · majentik
Params1.08B
Context128K
Smallest0.8 GB
ReasoningTool use
QW
Qwen3 Embedding 4B GGUF Q4 K M
Qwen · majentik
Params4.02B
Context40K
Q4_K_M2.5 GB
EmbeddingTool use
MI
MiniCPM5 1B Base
MiniCPM · majentik
Params1.08B
Context128K
Smallest1.2 GB
ReasoningTool use

Keep browsing