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.

Most downloadedNewestLargestLongest contextSmallest
FA
FastThink 0.5B Tiny
Fastthink · Hjgugugjhuhjggg
Params494M
Context32K
Smallest0.3 GB
Tool use
XD
my xdd Q2 K
Xdd · Hjgugugjhuhjggg
Params1.24B
Context128K
Smallest0.6 GB
Tool use
LL
Llama 3.2 3B Instruct
Llama · Hjgugugjhuhjggg
Params3.61B
Context128K
Smallest1.5 GB
Tool use
FG
fgfgfgf Q2 K
Fgfgfgf · Hjgugugjhuhjggg
Params3.61B
Context128K
Smallest1.5 GB
Tool use
LL
LLaMa3.1 1bit bitnet cuda Q2 K
Llama · Hjgugugjhuhjggg
Params101M
Context256
Smallest0.1 GB
Tool use
SE
semi final Q2 K
Semi · Hjgugugjhuhjggg
Params3.61B
Context128K
Smallest1.5 GB
Tool use
JA
Jaja small Q2 K
Jaja · Hjgugugjhuhjggg
Params135M
Context8K
Smallest0.1 GB
GGUF
LL
Llama 3.2 1B Instruct
Llama · Hjgugugjhuhjggg
Params1.24B
Context128K
Smallest0.6 GB
Tool use
LL
Llama 3.2 1B Instruct Abliterated
Llama · Hjgugugjhuhjggg
Params1.5B
Context128K
Smallest0.7 GB
Tool use
FG
fgfgx Q2 K
Fgfgx · Hjgugugjhuhjggg
Params626M
Context128K
Smallest0.3 GB
GGUF
GP
gpt2 Q2 K
Gpt · Hjgugugjhuhjggg
Params150M
Context1K
Smallest0.1 GB
GGUF
MA
Marco o1 Q2 K
Marco · Hjgugugjhuhjggg
Params7.62B
Context32K
Smallest3.0 GB
GGUF
ME
mergekit ties dkhnzcn Q2 K
Mergekit · Hjgugugjhuhjggg
Params3.61B
Context128K
Smallest1.5 GB
Tool use
SM
Small_Tiny_V1
Small · Hjgugugjhuhjggg
Params13M
Context1K
Smallest0.0 GB
GGUF
JA
Jaja small v2 Q2 K
Jaja · Hjgugugjhuhjggg
Params135M
Context8K
Smallest0.1 GB
GGUF
XD
xd 101 Q2 K
Hjgugugjhuhjggg
Params4.76B
Context128K
Smallest1.8 GB
GGUF
TE
testing semifinal Q2 K
Testing · Hjgugugjhuhjggg
Params3.61B
Context128K
Smallest1.5 GB
Tool use
ME
mergekit passthrough cijkogj Q2 K
Mergekit · Hjgugugjhuhjggg
Params889M
Context128K
Smallest0.5 GB
Tool use
ME
mergekit linear rfxmzdf Q2 K
Mergekit · Hjgugugjhuhjggg
Params3.61B
Context128K
Smallest1.5 GB
Tool use
ME
mergekit passthrough owrmdht Q2 K
Mergekit · Hjgugugjhuhjggg
Params1.24B
Context128K
Smallest0.6 GB
Tool use
MA
Marco o1 abliterated Q2 K
Marco · Hjgugugjhuhjggg
Params7.62B
Context32K
Smallest3.0 GB
GGUF
LL
Llama 3.2 1B
Llama · Hjgugugjhuhjggg
Params1.24B
Context128K
Smallest0.6 GB
GGUF
ME
mergekit ties dbpokuq Q2 K
Mergekit · Hjgugugjhuhjggg
Params3.61B
Context128K
Smallest1.5 GB
GGUF
ME
mergekit ties dkhnzcn IQ4 XS
Mergekit · Hjgugugjhuhjggg
Params3.61B
Context128K
Smallest2.0 GB
Tool use
ME
mergekit ties tzamfyy Q2 K
Mergekit · Hjgugugjhuhjggg
Params1.24B
Context128K
Smallest0.6 GB
GGUF
ME
mergekit ties tembqzx Q2 K
Mergekit · Hjgugugjhuhjggg
Params3.61B
Context128K
Smallest1.5 GB
Tool use
ME
mergekit ties ahipcqm Q2 K
Mergekit · Hjgugugjhuhjggg
Params3.61B
Context128K
Smallest1.5 GB
Tool use
ME
mergekit passthrough sppyqor Q2 K
Mergekit · Hjgugugjhuhjggg
Params323M
Context128K
Smallest0.2 GB
GGUF
ME
mergekit ties uoehqyz Q2 K
Mergekit · Hjgugugjhuhjggg
Params3.61B
Context128K
Smallest1.5 GB
Tool use
MA
Maixtchup Q2 K
Maixtchup · Hjgugugjhuhjggg
Params7.44B
Context128K
Smallest2.9 GB
Tool use

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).

Keep browsing