elkaioptimization/vllm-nvfp4-cuda-13

•Updated 10 months ago

vLLM NVFP4 CUDA 13 - Blackwell-optimized vLLM for NVFP4/FP8 serving

Image

2.6K

Tags for elkaioptimization/vllm-nvfp4-cuda-13

Sort by

TAG

qwen3-vl-8b-thinking-nvfp4-1.0

Last pushed 10 months by mutazai

docker pull elkaioptimization/vllm-nvfp4-cuda-13:qwen3-vl-8b-thinking-nvfp4-1.0

Digest	OS/ARCH	Compressed size
704c2cdeb48d	linux/arm64	17.09 GB

TAG

qwen3-vl-4b-thinking-nvfp4-1.0

Last pushed 10 months by mutazai

docker pull elkaioptimization/vllm-nvfp4-cuda-13:qwen3-vl-4b-thinking-nvfp4-1.0

Digest	OS/ARCH	Compressed size
7e0054c6ed63	linux/arm64	13.97 GB

TAG

qwen3-vl-2b-thinking-nvfp4-1.0

Last pushed 10 months by mutazai

docker pull elkaioptimization/vllm-nvfp4-cuda-13:qwen3-vl-2b-thinking-nvfp4-1.0

Digest	OS/ARCH	Compressed size
7ab530d687c5	linux/arm64	12.75 GB

TAG

nemotron3-30b-nvfp4-1.0

Last pushed 10 months by mutazai

docker pull elkaioptimization/vllm-nvfp4-cuda-13:nemotron3-30b-nvfp4-1.0

Digest	OS/ARCH	Compressed size
d2135f8a51d5	linux/arm64	27.27 GB

TAG

latest

Last pushed 10 months by mutazai

docker pull elkaioptimization/vllm-nvfp4-cuda-13:latest

Digest	OS/ARCH	Compressed size
d2135f8a51d5	linux/arm64	27.27 GB

TAG

1.1.0

Last pushed 10 months by mutazai

docker pull elkaioptimization/vllm-nvfp4-cuda-13:1.1.0

Digest	OS/ARCH	Compressed size
d2135f8a51d5	linux/arm64	27.27 GB

TAG

nemotron3-30b

Last pushed 10 months by mutazai

docker pull elkaioptimization/vllm-nvfp4-cuda-13:nemotron3-30b

Digest	OS/ARCH	Compressed size
d2135f8a51d5	linux/arm64	27.27 GB