GGUF models by ineosnexus

97 GGUF models quantized by ineosnexus on Hugging Face. Sizes run from 25.2B to 34.7B parameters. The longest trained context is 256K tokens.

Most downloadedNewestLargestLongest contextSmallest
AR
Gm4 31B arli it i1
Arli · ineosnexus
Params30.7B
Context256K
Smallest25.2 GB
ReasoningTool use
AR
Gm4 31B ara custom heretic it i1
Ara · ineosnexus
Params30.7B
Context256K
Smallest25.2 GB
ReasoningTool use
VE
Gm4 31B Versipellis i1
Versipellis · ineosnexus
Params30.7B
Context256K
Smallest25.2 GB
ReasoningTool use
ES
Gm4 31B Esmeralda i1
Esmeralda · ineosnexus
Params30.7B
Context256K
Smallest25.2 GB
GGUF
HA
Gm4 31B Harmonia i1
Harmonia · ineosnexus
Params30.7B
Context256K
Smallest25.2 GB
ReasoningTool use
FA
Gm4 31B Fabled i1
Fabled · ineosnexus
Params30.7B
Context256K
Smallest25.2 GB
ReasoningTool use
GE
Gm4 31B Gembrain i1
Gembrain · ineosnexus
Params30.7B
Context256K
Smallest25.2 GB
ReasoningTool use

Keep browsing