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.

Most downloadedNewestLargestLongest contextSmallest
AR
Artigenz Coder DS 6.7B Q5 K M
Artigenz · djuna
Params6.74B
Context16K
Smallest4.8 GB
Coding
JI
jina embeddings v2 base en Q5 K M
Jina · djuna
Params137M
Context8K
Smallest0.1 GB
Embedding
CH
MN Chinofun 12B 4.1 Q6 K
Chinofun · djuna
Params12.2B
Context128K
Smallest10.1 GB
GGUF
GS
G2 GSHT Q4 K S
Gsht · djuna
Params9.24B
Context8K
Smallest5.5 GB
GGUF
II
Q3 IIJAN 3B
Iijan · djuna
Params4.02B
Context256K
Smallest4.3 GB
GGUF
PR
L3.1 Promissum Mane 8B Della calc Q5 K M
Promissum · djuna
Params8.03B
Context128K
Smallest5.7 GB
GGUF
JI
jina embeddings v2 base code Q5 K M
Jina · djuna
Params160M
Context8K
Smallest0.1 GB
CodingEmbedding
JI
jina embeddings v2 small en Q5 K M
Jina · djuna
Params32M
Context8K
Smallest0.0 GB
Embedding
VE
Q2.5 Veltha 14B 0.5 Q5 K M
Veltha · djuna
Params14.8B
Context128K
Smallest10.5 GB
Tool use
CH
MN Chinofun Q4 K M
Chinofun · djuna
Params12.2B
Context1000K
Q4_K_M7.5 GB
Tool use
PU
L3.1 Purosani Q5 K M
Purosani · djuna
Params8.03B
Context128K
Smallest5.7 GB
GGUF
NO
G2 Noranum 27B Q3 K S
Noranum · djuna
Params27.2B
Context8K
Smallest12.2 GB
GGUF
NO
L3.1 Noraian Q5 K M
Noraian · djuna
Params8.03B
Context128K
Smallest5.7 GB
GGUF
ST
Stella Base En v2
Stella · djuna
Params109M
Context512
Smallest0.1 GB
Embedding
QW
Qwen2.5 7B Anvita Q4 K M
Qwen · djuna
Params7.62B
Context32K
Q4_K_M4.7 GB
GGUF
SU
L3.1 Suze Vume calc Q5 K M
Suze · djuna
Params8.03B
Context128K
Smallest5.7 GB
GGUF
TE
TEST Q2.5 AA Q8 0
Test · djuna
Params8.78B
Context128K
Smallest9.3 GB
GGUF
GE
GSHT GEMMAMA 16B Q3 K M
Gemma · djuna
Params14.8B
Context8K
Smallest7.4 GB
GGUF
TE
TEST OcerusBeam 7B Q5 K M
Test · djuna
Params7.24B
Context512K
Smallest5.1 GB
GGUF
GS
G2 GSHT 32K Q6 K
Gsht · djuna
Params9.24B
Context32K
Smallest7.6 GB
GGUF
PA
Q2.5 Partron 7B Q5 K M
Partron · djuna
Params7.61B
Context128K
Smallest5.4 GB
GGUF
FU
Q2.5 Fuppavy 7B Q5 K M
Fuppavy · djuna
Params7.61B
Context128K
Smallest5.4 GB
GGUF
GE
MT Gen3 gemma 2 9B Flip Q5 K M
Gemma · djuna
Params9.24B
Context8K
Smallest6.6 GB
GGUF
QW
qwen2.5 11B Mzy Q4 K M
Qwen · djuna
Params11.3B
Context32K
Q4_K_M6.9 GB
GGUF
TE
mergekit linear lyapgfy Q5 K M
Test · djuna
Params8.03B
Context128K
Smallest5.7 GB
GGUF
VE
Q2.5 Veltha 14B Q5 K M
Veltha · djuna
Params14.8B
Context128K
Smallest10.5 GB
Tool use
BO
L3.1 Boshima b FIX calc Q5 K M
Boshima · djuna
Params8.03B
Context128K
Smallest5.7 GB
Tool use
TE
TEST2 Q2.5 Lenned 14B Q5 K M
Test · djuna
Params14.8B
Context128K
Smallest10.5 GB
Tool use
GE
Gemma 2 gemmama 9b Q5 K M
Gemma · djuna
Params9.24B
Context8K
Smallest6.6 GB
GGUF
PU
L3.1 Purosani 1.5 8B Q5 K M
Purosani · djuna
Params8.03B
Context128K
Smallest5.7 GB
GGUF

About djuna on Hugging Face

djuna has published 41 GGUF models that ggufmodels.com tracks, across families such as Test, Gemma and Qwen. The most downloaded are Artigenz Coder DS 6.7B Q5 K M, jina embeddings v2 base en Q5 K M and MN Chinofun 12B 4.1 Q6 K.

The quants djuna publishes most often are Q5_K_M (26), Q8_0 (3), Q6_K (3) and Q4_K_S (3). Their Q4_K_M files range from 4.7 to 7.5 GB. Parameter counts run from 32M to 27.2B, and the longest trained context window is 1000K tokens.

Frequently asked questions

What GGUF models has djuna published?

41 models are listed here, mainly from the Test, Gemma and Qwen families. The most downloaded is Artigenz Coder DS 6.7B Q5 K M.

Which quants does djuna publish?

The most common are Q5_K_M (26 models), Q8_0 (3 models), Q6_K (3 models) and Q4_K_S (3 models).

Keep browsing