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