holtmann/llm-benchmark

•Updated 9 months ago

Benchmark suite for LLM inference on NVIDIA consumer GPUs (RTX 5060 Ti, 5070 Ti, 5090)

Image

Machine learning & AI

2.3K

Tags for holtmann/llm-benchmark

Sort by

TAG

20251219

Last pushed 9 months by holtmann

docker pull holtmann/llm-benchmark:20251219

Digest	OS/ARCH	Compressed size
feca39ff5d2b	linux/amd64	10.99 GB

TAG

latest

Last pushed 9 months by holtmann

docker pull holtmann/llm-benchmark:latest

Digest	OS/ARCH	Compressed size
feca39ff5d2b	linux/amd64	10.99 GB

TAG

v0.12.0

Last pushed 9 months by holtmann

docker pull holtmann/llm-benchmark:v0.12.0

Digest	OS/ARCH	Compressed size
68c8b123c232	linux/amd64	5.95 GB

TAG

v0.11.2_nvfp4

Last pushed 10 months by holtmann

docker pull holtmann/llm-benchmark:v0.11.2_nvfp4

Digest	OS/ARCH	Compressed size
b36cec384c3f	linux/amd64	6.81 GB