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.
QU
Gm4 31B Queen it i1
Queen · ineosnexus
Params30.7B
Context256K
Smallest25.2 GB
DA
Gm4 31B Dark Gemistry i1
Dark · ineosnexus
Params32.1B
Context256K
Smallest26.4 GB
QU
Gm4 31B Queen heretic it i1
Queen · ineosnexus
Params30.7B
Context256K
Smallest25.2 GB
DA
Gm4 31B Darwin Opus i1
Darwin · ineosnexus
Params30.7B
Context256K
Smallest25.2 GB
AB
Qw3.6 27B abliterated rMAX i1
Abliterated · ineosnexus
Params26.9B
Context256K
Smallest22.1 GB
DA
Qw3.6 36B Darwin Opus HERETIC i1
Darwin · ineosnexus
Params34.7B
Context256K
Smallest28.5 GB
DA
Gm4 31B DarkIdol it i1
Darkidol · ineosnexus
Params30.7B
Context256K
Smallest25.2 GB
GA
Gm4 31B Garnet it i1
Garnet · ineosnexus
Params30.7B
Context256K
Smallest25.2 GB
SP
Gm4 31B Sphinsikus Chronist i1
Sphinsikus · ineosnexus
Params30.7B
Context256K
Smallest25.2 GB
ES
Qw3.6 27B Esper3.1 i1
Esper · ineosnexus
Params26.9B
Context256K
Smallest22.1 GB
DA
Gm4 31B DarkIdol it FT i1
Darkidol · ineosnexus
Params30.7B
Context256K
Smallest25.2 GB
GA
Gm4 31B Garnet heretic it i1
Garnet · ineosnexus
Params30.7B
Context256K
Smallest25.2 GB
CL
Qw3.6 35B A3B Claude 4.7 Opus hui abliterated i1
Claude · ineosnexus
Params34.7B
Context256K
Smallest28.5 GB
AG
Gm4 31B Agares v1 i1
Agares · ineosnexus
Params30.7B
Context256K
Smallest25.2 GB
GA
Gm4 31B Garnet V2 heretic i1
Garnet · ineosnexus
Params30.7B
Context256K
Smallest25.2 GB
IN
Gm4 31B K1 v5 i1
Ineosnexus · ineosnexus
Params30.7B
Context256K
Smallest25.2 GB
CL
Qw3.6 35B A3B Claude 4.7 Opus Reasoning Distill i1
Claude · ineosnexus
Params34.7B
Context256K
Smallest28.5 GB
GO
Gm4 31B Goetia v1 i1
Goetia · ineosnexus
Params30.7B
Context256K
Smallest25.2 GB
SO
Qw3.6 27B SOM MPOA i1
Som · ineosnexus
Params26.9B
Context256K
Smallest22.1 GB
OP
Gm4 31b opus reasoning v5 i1
Opus · ineosnexus
Params30.7B
Context256K
Smallest25.2 GB
NE
Qw3.6 3.5 3 35B Nexus Coder heretic i1
Nexus · ineosnexus
Params34.7B
Context256K
Smallest28.5 GB
SD
Gm4 31B SDFT rp heretic it i1
Sdft · ineosnexus
Params30.7B
Context256K
Smallest25.2 GB
GE
Gm4 31B Gemsicle 31B i1
Gemsicle · ineosnexus
Params30.7B
Context256K
Smallest25.2 GB
AB
Qw3.6 35B A3B abliterated i1
Abliterated · ineosnexus
Params34.7B
Context256K
Smallest28.5 GB
HE
Gm4 31B HERETIC Thinking it i1
Heretic · ineosnexus
Params30.7B
Context256K
Smallest25.2 GB
GE
Gm4 26B A4B GemPT i1
Gempt · ineosnexus
Params25.2B
Context256K
Smallest22.6 GB
AB
Qw3.6 35B A3B abliterated MAX i1
Abliterated · ineosnexus
Params34.7B
Context256K
Smallest28.5 GB
CO
Gm4 31B Cognitive Uncensored it i1
Cognitive · ineosnexus
Params30.7B
Context256K
Smallest25.2 GB
SU
Gm4 26B super g multimodal abliterated i1
Super · ineosnexus
Params25.2B
Context256K
Smallest22.6 GB
HE
Gm4 26B A4B heretic i1
Heretic · ineosnexus
Params25.2B
Context256K
Smallest22.6 GB
About ineosnexus on Hugging Face
ineosnexus has published 97 GGUF models that ggufmodels.com tracks, across families such as Ineosnexus, Gembrain and Orn. The most downloaded are Gm4 31B Queen it i1, Gm4 31B Dark Gemistry i1 and Gm4 31B Queen heretic it i1.
The quants ineosnexus publishes most often are Q6_K (97). Parameter counts run from 25.2B to 34.7B, and the longest trained context window is 256K tokens.
Frequently asked questions
What GGUF models has ineosnexus published?
97 models are listed here, mainly from the Ineosnexus, Gembrain and Orn families. The most downloaded is Gm4 31B Queen it i1.
Which quants does ineosnexus publish?
The most common are Q6_K (97 models).