GGUF models by djuna
41 GGUF models quantized by djuna on Hugging Face. Sizes run from 32M to 27.2B parameters. The longest trained context is 1000K tokens.
CH
MN Chinofun 12B 4 Q6 K
Chinofun · djuna
Params12.2B
Context128K
Smallest10.1 GB
QW
Qwen2 1.5B Instruct
Qwen · djuna
Params1.54B
Context32K
Smallest1.6 GB
ET
L3.1 15B EtherealMaid t0.0001 alpha Q4 K S
Etherealmaid · djuna
Params15B
Context128K
Smallest8.6 GB
MI
MN Miuryra 18B Q3 K M
Miuryra · djuna
Params18.2B
Context1000K
Smallest9.0 GB
TE
TEST Ocerus 7B Q5 K M
Test · djuna
Params7.24B
Context32K
Smallest5.1 GB
GE
Gemma 2 gemmama 9b Q4 K S
Gemma · djuna
Params9.24B
Context8K
Smallest5.5 GB
FO
L3.1 ForStHS Q5 K M
Forsths · djuna
Params8.03B
Context128K
Smallest5.7 GB
LU
MN Lulanum 12B FIX Q5 K M
Lulanum · djuna
Params12.2B
Context1000K
Smallest8.7 GB
TE
mergekit dare linear xaazcaj Q5 K M
Test · djuna
Params8.03B
Context128K
Smallest5.7 GB
TE
mergekit della linear qaxucjoo Q5 K M
Test · djuna
Params8.03B
Context128K
Smallest5.7 GB
TE
TEST3 Q2.5 Lenned 14B Q5 K M
Test · djuna
Params14.8B
Context128K
Smallest10.5 GB