Sign inSign up

synonexthub/llama.cpp

By synonexthub

•Updated 3 months ago

Build of `llama.cpp` serve, compiled against *NVIDIA CUDA 12.4.1*, for running LLMs like *Gemma 4*.

Image
API management
Machine learning & AI
0

262

Tags for synonexthub/llama.cpp

Sort by

TAG

server-cuda-12.4.1-ada_lovelace

Last pushed 3 months by synonexthub

docker pull synonexthub/llama.cpp:server-cuda-12.4.1-ada_lovelace
DigestOS/ARCHCompressed size

63f5d5f01fc4

linux/amd64

1.44 GB

TAG

server-cuda-12.4.1-ampere

Last pushed 3 months by synonexthub

docker pull synonexthub/llama.cpp:server-cuda-12.4.1-ampere
DigestOS/ARCHCompressed size

13ddbc4e37e9

linux/amd64

1.44 GB