GGUF models by ukung

43 GGUF models quantized by ukung on Hugging Face. Sizes run from 135M to 14B parameters. The longest trained context is 256K tokens.

Most downloadedNewestLargestLongest contextSmallest
KO
komodo 7b base
Komodo · ukung
Params6.76B
Context4K
Q4_K_M4.1 GB
GGUF
NU
Nusantara 4b Indo Chat
Nusantara · ukung
Params3.95B
Context32K
Q4_K_M2.5 GB
GGUF
QW
gte-Qwen1.5-7B-instruct
Qwen · ukung
Params7.72B
Context32K
Q4_K_M4.8 GB
GGUF
LL
Small Llama3 6B
Llama · ukung
Params6.29B
Context8K
Q4_K_M3.9 GB
GGUF
LL
Open Llama 3B FineTune
Llama · ukung
Params3.43B
Context2K
Q4_K_M2.6 GB
GGUF
AU
AutoCoder S 6.7B
Autocoder · ukung
Params6.74B
Context16K
Q4_K_M4.1 GB
Coding
QW
qwen2-7b
Qwen · ukung
Params7.62B
Context32K
Q4_K_M4.7 GB
GGUF
NU
Nusantara 0.8b Indo Chat
Nusantara · ukung
Params825M
Context32K
Q4_K_M0.5 GB
GGUF
SE
semantic lite
Semantic · ukung
Params250M
Context40K
Smallest0.2 GB
Embedding
PI
PipAI SQL 1.3b
Pipai · ukung
Params1.35B
Context16K
Q4_K_M0.9 GB
GGUF
QW
Qwen2 1.5B Instruct
Qwen · ukung
Params1.54B
Context32K
Q4_K_M1.0 GB
GGUF
MI
Mistral Instruct V0.3 INDO
Mistral · ukung
Params7.25B
Context32K
Q4_K_M4.4 GB
GGUF
TI
TinyMistral 6x248M Instruct
Tinymistral · ukung
Params1B
Context32K
Q4_K_M0.6 GB
GGUF
NU
Nusantara 2.7b Indo Chat v0.2
Nusantara · ukung
Params2.65B
Context8K
Q4_K_M1.7 GB
GGUF
LL
cendol llama2 7b inst
Llama · ukung
Params6.74B
Context4K
Q4_K_M4.1 GB
GGUF
WI
WizardLM-2-7B
Wizardlm · ukung
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
DE
DeepSeek SQL Expert
DeepSeek · ukung
Params1.35B
Context16K
Q4_K_M0.9 GB
GGUF
GE
Gemma 2B INDO V2
Gemma · ukung
Params2.51B
Context8K
Q4_K_M1.6 GB
GGUF
PH
Phi 3 mini 4k instruct
Phi · ukung
Params3.82B
Context4K
Q4_K_M2.4 GB
GGUF
TI
TinyLlama 1.1B PythonSkill
Tinyllama · ukung
Params1.1B
Context2K
Q4_K_M0.7 GB
GGUF
GE
Gemma2B Indo FineTune
Gemma · ukung
Params2.51B
Context8K
Q4_K_M1.6 GB
GGUF
QW
qwen2-0_5b
Qwen · ukung
Params630M
Context32K
Q4_K_M0.5 GB
GGUF
GE
Gemma2B Text To SQL Expert
Gemma · ukung
Params2.51B
Context8K
Q4_K_M1.6 GB
GGUF
TI
TinyLlama 1.1B indo v1
Tinyllama · ukung
Params1.1B
Context2K
Q4_K_M0.7 GB
GGUF
LL
Llama3 IndoTunned
Llama · ukung
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
MiniCPM Llama3 V 2 5
Llama · ukung
Params8.03B
Context8K
Smallest3.2 GB
GGUF
NU
Nusantara 1.8b Indo Chat
Nusantara · ukung
Params1.84B
Context8K
Q4_K_M1.2 GB
GGUF
TI
TinyMixtral 32x248M
Tinymixtral · ukung
Params4.93B
Context32K
Q4_K_M3.0 GB
GGUF
NU
Nusantara 7b Indo Chat
Nusantara · ukung
Params7.72B
Context32K
Q4_K_M4.8 GB
GGUF
PH
Phi 3 medium 128k instruct Rev2
Phi · ukung
Params14B
Context128K
Q4_K_M8.6 GB
GGUF

About ukung on Hugging Face

ukung has published 43 GGUF models that ggufmodels.com tracks, across families such as Qwen, Nusantara and Llama. The most downloaded are komodo 7b base, Nusantara 4b Indo Chat and gte-Qwen1.5-7B-instruct.

The quants ukung publishes most often are Q8_0 (37), Q4_K_M (34), Q4_0 (33) and Q3_K_L (33). Their Q4_K_M files range from 0.2 to 8.6 GB. Parameter counts run from 135M to 14B, and the longest trained context window is 256K tokens.

Frequently asked questions

What GGUF models has ukung published?

43 models are listed here, mainly from the Qwen, Nusantara and Llama families. The most downloaded is komodo 7b base.

Which quants does ukung publish?

The most common are Q8_0 (37 models), Q4_K_M (34 models), Q4_0 (33 models) and Q3_K_L (33 models).

Keep browsing