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.

Most downloadedNewestLargestLongest contextSmallest
NE
Neural-SOVLish-Devil-8B-L3
Neural · Lewdiculous
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
MU
Multi Verse RP 7B GGUF IQ Imatrix
Multi · Lewdiculous
Params7.24B
Context32K
Q4_K_M4.4 GB
Roleplay
TE
Test0 SLIDE GGUF IQ Imatrix
Test · Lewdiculous
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
LLaMa-3-CursedStock-v1.8-8B
Llama · Lewdiculous
Params8B
Context8K
Q4_K_M4.9 GB
GGUF
OR
Orthocopter_8B
Orthocopter · Lewdiculous
Params8.03B
Context8K
Q4_K_M4.9 GB
Roleplay
LL
Mahou-1.2-llama3-8B
Llama · Lewdiculous
Params8.03B
Context8K
Q4_K_M4.9 GB
Roleplay
ER
Paradigm 7B GGUF IQ Imatrix
Eris · Lewdiculous
Params7.24B
Context32K
Q4_K_M4.4 GB
Roleplay
DA
Datura 7B GGUF Imatrix
Datura · Lewdiculous
Params7.24B
Context32K
Q4_K_M4.4 GB
Roleplay
LL
llama3-8B-aifeifei-1.2
Llama · Lewdiculous
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
llama3-8B-aifeifei-1.1
Llama · Lewdiculous
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
llama.cpp 11077 test 01
Llama · Lewdiculous
Params8.03B
Context8K
Smallest4.0 GB
Tool use
LL
llama3-8B-feifei-1.0
Llama · Lewdiculous
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF

Keep browsing