GGUF models: cc-by-nc-2.0 license
74 GGUF models listed under the cc-by-nc-2.0 license on Hugging Face. Always read the license text before commercial use. Sizes run from 69M to 120B parameters. The longest trained context is 1000K tokens.
LA
laserxtral sota
Laserxtral · Absolucy
Params24.2B
Context32K
Smallest6.4 GB
MI
miquliz 120b v2.0 iMat
Miquliz · dranger003
Params120B
Context32K
Smallest31.8 GB
LL
Ko En Llama2 13b
Llama · tensorblock
Params13B
Context2K
Smallest4.9 GB
CO
core 3 kuno royale v2 7b
Core · RichardErkhov
Params7.24B
Context8K
Q4_K_M4.4 GB
LO
Loquace 7B Q3 K S
Loquace · antoste
Params7.22B
Context2K
Smallest3.9 GB
CO
core 3 kuno dogwalker 7b
Core · RichardErkhov
Params7.24B
Context8K
Q4_K_M4.4 GB
QW
qwen2.5 14b coder lora Q8 0
Qwen · Nick0925
Params69M
Context—
Smallest0.1 GB
LL
BlackSheep Llama3.2 3B
Llama · Notenufftime
Params3.21B
Context128K
Smallest3.4 GB
CO
core 3 kuno dogpark 7b
Core · RichardErkhov
Params7.24B
Context8K
Q4_K_M4.4 GB
MI
fades mistral v02
Mistral · maxime-antoine-dev
Params7.24B
Context32K
Q4_K_M4.4 GB
QW
qwen2.5 14b coder lora
Qwen · Nick0925
Params69M
Context—
Smallest0.3 GB
MI
mistral 7b q4
Mistral · suryajit27
Params7.25B
Context32K
Smallest4.1 GB
LL
Ko En Llama2 13b
Llama · tensorblock
Params13.2B
Context2K
Smallest5.0 GB
BI
ds 4bit
Bit · datastreams
Params12.9B
Context2K
Smallest7.3 GB