GGUF models by Hjgugugjhuhjggg
37 GGUF models quantized by Hjgugugjhuhjggg on Hugging Face. Sizes run from 13M to 8.04B parameters. The longest trained context is 128K tokens.
FA
FastThink 0.5B Tiny
Fastthink · Hjgugugjhuhjggg
Params494M
Context32K
Smallest0.3 GB
XD
my xdd Q2 K
Xdd · Hjgugugjhuhjggg
Params1.24B
Context128K
Smallest0.6 GB
LL
Llama 3.2 3B Instruct
Llama · Hjgugugjhuhjggg
Params3.61B
Context128K
Smallest1.5 GB
FG
fgfgfgf Q2 K
Fgfgfgf · Hjgugugjhuhjggg
Params3.61B
Context128K
Smallest1.5 GB
LL
LLaMa3.1 1bit bitnet cuda Q2 K
Llama · Hjgugugjhuhjggg
Params101M
Context256
Smallest0.1 GB
SE
semi final Q2 K
Semi · Hjgugugjhuhjggg
Params3.61B
Context128K
Smallest1.5 GB
JA
Jaja small Q2 K
Jaja · Hjgugugjhuhjggg
Params135M
Context8K
Smallest0.1 GB
LL
Llama 3.2 1B Instruct
Llama · Hjgugugjhuhjggg
Params1.24B
Context128K
Smallest0.6 GB
LL
Llama 3.2 1B Instruct Abliterated
Llama · Hjgugugjhuhjggg
Params1.5B
Context128K
Smallest0.7 GB
FG
fgfgx Q2 K
Fgfgx · Hjgugugjhuhjggg
Params626M
Context128K
Smallest0.3 GB
GP
gpt2 Q2 K
Gpt · Hjgugugjhuhjggg
Params150M
Context1K
Smallest0.1 GB
MA
Marco o1 Q2 K
Marco · Hjgugugjhuhjggg
Params7.62B
Context32K
Smallest3.0 GB
ME
mergekit ties dkhnzcn Q2 K
Mergekit · Hjgugugjhuhjggg
Params3.61B
Context128K
Smallest1.5 GB
SM
Small_Tiny_V1
Small · Hjgugugjhuhjggg
Params13M
Context1K
Smallest0.0 GB
JA
Jaja small v2 Q2 K
Jaja · Hjgugugjhuhjggg
Params135M
Context8K
Smallest0.1 GB
XD
xd 101 Q2 K
Hjgugugjhuhjggg
Params4.76B
Context128K
Smallest1.8 GB
TE
testing semifinal Q2 K
Testing · Hjgugugjhuhjggg
Params3.61B
Context128K
Smallest1.5 GB
ME
mergekit passthrough cijkogj Q2 K
Mergekit · Hjgugugjhuhjggg
Params889M
Context128K
Smallest0.5 GB
ME
mergekit linear rfxmzdf Q2 K
Mergekit · Hjgugugjhuhjggg
Params3.61B
Context128K
Smallest1.5 GB
ME
mergekit passthrough owrmdht Q2 K
Mergekit · Hjgugugjhuhjggg
Params1.24B
Context128K
Smallest0.6 GB
MA
Marco o1 abliterated Q2 K
Marco · Hjgugugjhuhjggg
Params7.62B
Context32K
Smallest3.0 GB
LL
Llama 3.2 1B
Llama · Hjgugugjhuhjggg
Params1.24B
Context128K
Smallest0.6 GB
ME
mergekit ties dbpokuq Q2 K
Mergekit · Hjgugugjhuhjggg
Params3.61B
Context128K
Smallest1.5 GB
ME
mergekit ties dkhnzcn IQ4 XS
Mergekit · Hjgugugjhuhjggg
Params3.61B
Context128K
Smallest2.0 GB
ME
mergekit ties tzamfyy Q2 K
Mergekit · Hjgugugjhuhjggg
Params1.24B
Context128K
Smallest0.6 GB
ME
mergekit ties tembqzx Q2 K
Mergekit · Hjgugugjhuhjggg
Params3.61B
Context128K
Smallest1.5 GB
ME
mergekit ties ahipcqm Q2 K
Mergekit · Hjgugugjhuhjggg
Params3.61B
Context128K
Smallest1.5 GB
ME
mergekit passthrough sppyqor Q2 K
Mergekit · Hjgugugjhuhjggg
Params323M
Context128K
Smallest0.2 GB
ME
mergekit ties uoehqyz Q2 K
Mergekit · Hjgugugjhuhjggg
Params3.61B
Context128K
Smallest1.5 GB
MA
Maixtchup Q2 K
Maixtchup · Hjgugugjhuhjggg
Params7.44B
Context128K
Smallest2.9 GB
About Hjgugugjhuhjggg on Hugging Face
Hjgugugjhuhjggg has published 37 GGUF models that ggufmodels.com tracks, across families such as Mergekit, Llama and Jaja. The most downloaded are FastThink 0.5B Tiny, my xdd Q2 K and Llama 3.2 3B Instruct.
The quants Hjgugugjhuhjggg publishes most often are Q2_K (36) and IQ4_XS (1). Parameter counts run from 13M to 8.04B, and the longest trained context window is 128K tokens.
Frequently asked questions
What GGUF models has Hjgugugjhuhjggg published?
37 models are listed here, mainly from the Mergekit, Llama and Jaja families. The most downloaded is FastThink 0.5B Tiny.
Which quants does Hjgugugjhuhjggg publish?
The most common are Q2_K (36 models) and IQ4_XS (1 models).