GGUF models by Stark2008

48 GGUF models quantized by Stark2008 on Hugging Face. Sizes run from 3.82B to 21.4B parameters. The longest trained context is 1000K tokens.

Most downloadedNewestLargestLongest contextSmallest
LL
Llama 3 8B Instruct dare linear Q6 K
Llama · Stark2008
Params8.03B
Context8K
Smallest6.6 GB
GGUF
MI
Infinity Instruct 3M 0613 Mistral 7B
Mistral · Stark2008
Params7.24B
Context32K
Smallest5.9 GB
GGUF
LL
Llama 3 8B Instruct dare ties density 0.7 Q6 K
Llama · Stark2008
Params8.03B
Context8K
Smallest6.6 GB
GGUF
ST
StarFusion alpha1 Q6 K
Starfusion · Stark2008
Params7.24B
Context8K
Smallest5.9 GB
GGUF
DI
dictalm2 it qa fine tune Q4 K M
Dictalm · Stark2008
Params7.25B
Context32K
Q4_K_M4.4 GB
GGUF
DI
dictalm2 it qa fine tune Q4 0
Dictalm · Stark2008
Params7.25B
Context32K
Smallest4.1 GB
GGUF
HE
HebGutenLaser
Hebgutenlaser · Stark2008
Params7.24B
Context32K
Smallest5.9 GB
GGUF
MI
romulus mistral nemo 12b simpo Q3 K L
Mistral · Stark2008
Params12.2B
Context1000K
Smallest6.6 GB
GGUF
LL
Llama Phi 3 DoRA Q8 0
Llama · Stark2008
Params3.82B
Context4K
Smallest4.1 GB
GGUF
DI
dictalm2 it qa fine tune IQ4 NL
Dictalm · Stark2008
Params7.25B
Context32K
Smallest4.1 GB
GGUF
GE
Gemma2 9b it train6 Q6 K
Gemma · Stark2008
Params9.24B
Context8K
Smallest7.6 GB
GGUF
WI
WizardLM 13B V1.0
Wizardlm · Stark2008
Params13B
Context2K
Smallest6.9 GB
GGUF
WE
WestlakeMaziyar 7B slerp Q6 K
Westlakemaziyar · Stark2008
Params7.24B
Context32K
Smallest5.9 GB
GGUF
LL
Llama 3 8B Instruct dare ties density 0.9 Q6 K
Llama · Stark2008
Params8.03B
Context8K
Smallest6.6 GB
GGUF
NE
Neuralcoven 7B slerp Q6 K
Neuralcoven · Stark2008
Params7.24B
Context32K
Smallest5.9 GB
GGUF
GU
GutenLaserPi
Gutenlaserpi · Stark2008
Params7.24B
Context32K
Smallest5.9 GB
GGUF
FI
Final_Model_Test_V2
Final · Stark2008
Params21.4B
Context32K
Smallest8.1 GB
GGUF
LL
Llama 3 8B Instruct dare ties density 0.3 Q6 K
Llama · Stark2008
Params8.03B
Context8K
Smallest6.6 GB
GGUF

Keep browsing