GGUF models by Lewdiculous
162 GGUF models quantized by Lewdiculous on Hugging Face. Sizes run from 3.95B to 14.8B parameters. The longest trained context is 1000K tokens.
NE
Neural-SOVLish-Devil-8B-L3
Neural · Lewdiculous
Params8.03B
Context8K
Q4_K_M4.9 GB
MU
Multi Verse RP 7B GGUF IQ Imatrix
Multi · Lewdiculous
Params7.24B
Context32K
Q4_K_M4.4 GB
TE
Test0 SLIDE GGUF IQ Imatrix
Test · Lewdiculous
Params8.03B
Context8K
Q4_K_M4.9 GB
LL
LLaMa-3-CursedStock-v1.8-8B
Llama · Lewdiculous
Params8B
Context8K
Q4_K_M4.9 GB
OR
Orthocopter_8B
Orthocopter · Lewdiculous
Params8.03B
Context8K
Q4_K_M4.9 GB
LL
Mahou-1.2-llama3-8B
Llama · Lewdiculous
Params8.03B
Context8K
Q4_K_M4.9 GB
ER
Paradigm 7B GGUF IQ Imatrix
Eris · Lewdiculous
Params7.24B
Context32K
Q4_K_M4.4 GB
DA
Datura 7B GGUF Imatrix
Datura · Lewdiculous
Params7.24B
Context32K
Q4_K_M4.4 GB
LL
llama3-8B-aifeifei-1.2
Llama · Lewdiculous
Params8.03B
Context8K
Q4_K_M4.9 GB
LL
llama3-8B-aifeifei-1.1
Llama · Lewdiculous
Params8.03B
Context8K
Q4_K_M4.9 GB
LL
llama.cpp 11077 test 01
Llama · Lewdiculous
Params8.03B
Context8K
Smallest4.0 GB
LL
llama3-8B-feifei-1.0
Llama · Lewdiculous
Params8.03B
Context8K
Q4_K_M4.9 GB