NVIDIA-Nemotron-Nano-12B-v2-VL-BF16

52.2K
63
12.0B
—
by
nvidia
Image Model
OTHER
12B params
Fair
52K downloads
Community-tested
Try on Hugging FaceAdd to Compare
Edge AI:
Mobile
Laptop
Server
27GB+ RAM
Mobile
Laptop
Server
Quick Summary

Description: NVIDIA Nemotron Nano v2 12B VL model enables multi-image reasoning and video understanding, along with strong document intelligence, visual Q&A and summarization capabilities.

Device Compatibility

Mobile
4-6GB RAM
Laptop
16GB RAM
Server
GPU
Minimum Recommended
12GB+ RAM

Code Examples

Model Version(s):text
pip install causal_conv1d "transformers>4.53,<4.54" torch timm "mamba-ssm==2.2.5" accelerate open_clip_torch numpy pillow
Model Version(s):text
pip install causal_conv1d "transformers>4.53,<4.54" torch timm "mamba-ssm==2.2.5" accelerate open_clip_torch numpy pillow
Model Version(s):text
pip install causal_conv1d "transformers>4.53,<4.54" torch timm "mamba-ssm==2.2.5" accelerate open_clip_torch numpy pillow
Model Version(s):text
pip install causal_conv1d "transformers>4.53,<4.54" torch timm "mamba-ssm==2.2.5" accelerate open_clip_torch numpy pillow
Model Version(s):text
pip install causal_conv1d "transformers>4.53,<4.54" torch timm "mamba-ssm==2.2.5" accelerate open_clip_torch numpy pillow
Model Version(s):text
pip install causal_conv1d "transformers>4.53,<4.54" torch timm "mamba-ssm==2.2.5" accelerate open_clip_torch numpy pillow
Model Version(s):text
pip install causal_conv1d "transformers>4.53,<4.54" torch timm "mamba-ssm==2.2.5" accelerate open_clip_torch numpy pillow
Model Version(s):text
pip install causal_conv1d "transformers>4.53,<4.54" torch timm "mamba-ssm==2.2.5" accelerate open_clip_torch numpy pillow
Model Version(s):text
pip install causal_conv1d "transformers>4.53,<4.54" torch timm "mamba-ssm==2.2.5" accelerate open_clip_torch numpy pillow
Model Version(s):text
pip install causal_conv1d "transformers>4.53,<4.54" torch timm "mamba-ssm==2.2.5" accelerate open_clip_torch numpy pillow
Model Version(s):text
pip install causal_conv1d "transformers>4.53,<4.54" torch timm "mamba-ssm==2.2.5" accelerate open_clip_torch numpy pillow
Model Version(s):text
pip install causal_conv1d "transformers>4.53,<4.54" torch timm "mamba-ssm==2.2.5" accelerate open_clip_torch numpy pillow
Model Version(s):text
pip install causal_conv1d "transformers>4.53,<4.54" torch timm "mamba-ssm==2.2.5" accelerate open_clip_torch numpy pillow
Model Version(s):text
pip install causal_conv1d "transformers>4.53,<4.54" torch timm "mamba-ssm==2.2.5" accelerate open_clip_torch numpy pillow
Model Version(s):text
pip install causal_conv1d "transformers>4.53,<4.54" torch timm "mamba-ssm==2.2.5" accelerate open_clip_torch numpy pillow
Model Version(s):text
pip install causal_conv1d "transformers>4.53,<4.54" torch timm "mamba-ssm==2.2.5" accelerate open_clip_torch numpy pillow
Model Version(s):text
pip install causal_conv1d "transformers>4.53,<4.54" torch timm "mamba-ssm==2.2.5" accelerate open_clip_torch numpy pillow
Model Version(s):text
pip install causal_conv1d "transformers>4.53,<4.54" torch timm "mamba-ssm==2.2.5" accelerate open_clip_torch numpy pillow
Model Version(s):text
pip install causal_conv1d "transformers>4.53,<4.54" torch timm "mamba-ssm==2.2.5" accelerate open_clip_torch numpy pillow
Model Version(s):text
pip install causal_conv1d "transformers>4.53,<4.54" torch timm "mamba-ssm==2.2.5" accelerate open_clip_torch numpy pillow
Model Version(s):text
pip install causal_conv1d "transformers>4.53,<4.54" torch timm "mamba-ssm==2.2.5" accelerate open_clip_torch numpy pillow
Model Version(s):text
pip install causal_conv1d "transformers>4.53,<4.54" torch timm "mamba-ssm==2.2.5" accelerate open_clip_torch numpy pillow
Model Version(s):text
pip install causal_conv1d "transformers>4.53,<4.54" torch timm "mamba-ssm==2.2.5" accelerate open_clip_torch numpy pillow
Model Version(s):text
pip install causal_conv1d "transformers>4.53,<4.54" torch timm "mamba-ssm==2.2.5" accelerate open_clip_torch numpy pillow
Model Version(s):text
pip install causal_conv1d "transformers>4.53,<4.54" torch timm "mamba-ssm==2.2.5" accelerate open_clip_torch numpy pillow
Model Version(s):text
pip install causal_conv1d "transformers>4.53,<4.54" torch timm "mamba-ssm==2.2.5" accelerate open_clip_torch numpy pillow
Model Version(s):text
pip install causal_conv1d "transformers>4.53,<4.54" torch timm "mamba-ssm==2.2.5" accelerate open_clip_torch numpy pillow
Model Version(s):text
pip install causal_conv1d "transformers>4.53,<4.54" torch timm "mamba-ssm==2.2.5" accelerate open_clip_torch numpy pillow
Model Version(s):text
pip install causal_conv1d "transformers>4.53,<4.54" torch timm "mamba-ssm==2.2.5" accelerate open_clip_torch numpy pillow
Model Version(s):text
pip install causal_conv1d "transformers>4.53,<4.54" torch timm "mamba-ssm==2.2.5" accelerate open_clip_torch numpy pillow
Model Version(s):text
pip install causal_conv1d "transformers>4.53,<4.54" torch timm "mamba-ssm==2.2.5" accelerate open_clip_torch numpy pillow
Model Version(s):text
pip install causal_conv1d "transformers>4.53,<4.54" torch timm "mamba-ssm==2.2.5" accelerate open_clip_torch numpy pillow
Model Version(s):text
pip install causal_conv1d "transformers>4.53,<4.54" torch timm "mamba-ssm==2.2.5" accelerate open_clip_torch numpy pillow
Model Version(s):text
pip install causal_conv1d "transformers>4.53,<4.54" torch timm "mamba-ssm==2.2.5" accelerate open_clip_torch numpy pillow
Model Version(s):text
pip install causal_conv1d "transformers>4.53,<4.54" torch timm "mamba-ssm==2.2.5" accelerate open_clip_torch numpy pillow
Model Version(s):text
pip install causal_conv1d "transformers>4.53,<4.54" torch timm "mamba-ssm==2.2.5" accelerate open_clip_torch numpy pillow
Model Version(s):text
pip install causal_conv1d "transformers>4.53,<4.54" torch timm "mamba-ssm==2.2.5" accelerate open_clip_torch numpy pillow
Model Version(s):text
pip install causal_conv1d "transformers>4.53,<4.54" torch timm "mamba-ssm==2.2.5" accelerate open_clip_torch numpy pillow
Model Version(s):text
pip install causal_conv1d "transformers>4.53,<4.54" torch timm "mamba-ssm==2.2.5" accelerate open_clip_torch numpy pillow
Model Version(s):text
pip install causal_conv1d "transformers>4.53,<4.54" torch timm "mamba-ssm==2.2.5" accelerate open_clip_torch numpy pillow
Model Version(s):text
pip install causal_conv1d "transformers>4.53,<4.54" torch timm "mamba-ssm==2.2.5" accelerate open_clip_torch numpy pillow
Inference with vLLMbashvllm
!VLLM_USE_PRECOMPILED=1 pip install git+https://github.com/vllm-project/vllm.git@main
Inference with vLLMbashvllm
!VLLM_USE_PRECOMPILED=1 pip install git+https://github.com/vllm-project/vllm.git@main
Inference with vLLMbashvllm
!VLLM_USE_PRECOMPILED=1 pip install git+https://github.com/vllm-project/vllm.git@main
Inference with vLLMbashvllm
!VLLM_USE_PRECOMPILED=1 pip install git+https://github.com/vllm-project/vllm.git@main
Inference with vLLMbashvllm
!VLLM_USE_PRECOMPILED=1 pip install git+https://github.com/vllm-project/vllm.git@main
Inference with vLLMbashvllm
!VLLM_USE_PRECOMPILED=1 pip install git+https://github.com/vllm-project/vllm.git@main
Inference with vLLMbashvllm
!VLLM_USE_PRECOMPILED=1 pip install git+https://github.com/vllm-project/vllm.git@main
Inference with vLLMbashvllm
!VLLM_USE_PRECOMPILED=1 pip install git+https://github.com/vllm-project/vllm.git@main
Inference with vLLMbashvllm
!VLLM_USE_PRECOMPILED=1 pip install git+https://github.com/vllm-project/vllm.git@main
Inference with vLLMbashvllm
!VLLM_USE_PRECOMPILED=1 pip install git+https://github.com/vllm-project/vllm.git@main
Inference with vLLMbashvllm
!VLLM_USE_PRECOMPILED=1 pip install git+https://github.com/vllm-project/vllm.git@main
Inference with vLLMbashvllm
!VLLM_USE_PRECOMPILED=1 pip install git+https://github.com/vllm-project/vllm.git@main
Inference with vLLMbashvllm
!VLLM_USE_PRECOMPILED=1 pip install git+https://github.com/vllm-project/vllm.git@main
Inference with vLLMbashvllm
!VLLM_USE_PRECOMPILED=1 pip install git+https://github.com/vllm-project/vllm.git@main
Inference with vLLMbashvllm
!VLLM_USE_PRECOMPILED=1 pip install git+https://github.com/vllm-project/vllm.git@main
Inference with vLLMbashvllm
!VLLM_USE_PRECOMPILED=1 pip install git+https://github.com/vllm-project/vllm.git@main
Inference with vLLMbashvllm
!VLLM_USE_PRECOMPILED=1 pip install git+https://github.com/vllm-project/vllm.git@main
Inference with vLLMbashvllm
!VLLM_USE_PRECOMPILED=1 pip install git+https://github.com/vllm-project/vllm.git@main
Inference with vLLMbashvllm
!VLLM_USE_PRECOMPILED=1 pip install git+https://github.com/vllm-project/vllm.git@main
Inference with vLLMbashvllm
!VLLM_USE_PRECOMPILED=1 pip install git+https://github.com/vllm-project/vllm.git@main
Inference with vLLMbashvllm
!VLLM_USE_PRECOMPILED=1 pip install git+https://github.com/vllm-project/vllm.git@main
Inference with vLLMbashvllm
!VLLM_USE_PRECOMPILED=1 pip install git+https://github.com/vllm-project/vllm.git@main
Inference with vLLMbashvllm
!VLLM_USE_PRECOMPILED=1 pip install git+https://github.com/vllm-project/vllm.git@main
Inference with vLLMbashvllm
!VLLM_USE_PRECOMPILED=1 pip install git+https://github.com/vllm-project/vllm.git@main
Inference with vLLMbashvllm
!VLLM_USE_PRECOMPILED=1 pip install git+https://github.com/vllm-project/vllm.git@main
Inference with vLLMbashvllm
!VLLM_USE_PRECOMPILED=1 pip install git+https://github.com/vllm-project/vllm.git@main
Inference with vLLMbashvllm
!VLLM_USE_PRECOMPILED=1 pip install git+https://github.com/vllm-project/vllm.git@main
Inference with vLLMbashvllm
!VLLM_USE_PRECOMPILED=1 pip install git+https://github.com/vllm-project/vllm.git@main
Inference with vLLMbashvllm
!VLLM_USE_PRECOMPILED=1 pip install git+https://github.com/vllm-project/vllm.git@main
Inference with vLLMbashvllm
!VLLM_USE_PRECOMPILED=1 pip install git+https://github.com/vllm-project/vllm.git@main
Inference with vLLMbashvllm
!VLLM_USE_PRECOMPILED=1 pip install git+https://github.com/vllm-project/vllm.git@main
Inference with vLLMbashvllm
!VLLM_USE_PRECOMPILED=1 pip install git+https://github.com/vllm-project/vllm.git@main
Inference with vLLMbashvllm
!VLLM_USE_PRECOMPILED=1 pip install git+https://github.com/vllm-project/vllm.git@main
Inference with vLLMbashvllm
!VLLM_USE_PRECOMPILED=1 pip install git+https://github.com/vllm-project/vllm.git@main
Inference with vLLMbashvllm
!VLLM_USE_PRECOMPILED=1 pip install git+https://github.com/vllm-project/vllm.git@main
Inference with vLLMbashvllm
!VLLM_USE_PRECOMPILED=1 pip install git+https://github.com/vllm-project/vllm.git@main
Inference with vLLMbashvllm
!VLLM_USE_PRECOMPILED=1 pip install git+https://github.com/vllm-project/vllm.git@main
Inference with vLLMbashvllm
!VLLM_USE_PRECOMPILED=1 pip install git+https://github.com/vllm-project/vllm.git@main
Inference with vLLMbashvllm
!VLLM_USE_PRECOMPILED=1 pip install git+https://github.com/vllm-project/vllm.git@main
Inference with vLLMbashvllm
!VLLM_USE_PRECOMPILED=1 pip install git+https://github.com/vllm-project/vllm.git@main
Inference with vLLMbashvllm
!VLLM_USE_PRECOMPILED=1 pip install git+https://github.com/vllm-project/vllm.git@main
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16 --trust-remote-code --dtype bfloat16 --video-pruning-rate 0
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16 --trust-remote-code --dtype bfloat16 --video-pruning-rate 0
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16 --trust-remote-code --dtype bfloat16 --video-pruning-rate 0
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16 --trust-remote-code --dtype bfloat16 --video-pruning-rate 0
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16 --trust-remote-code --dtype bfloat16 --video-pruning-rate 0
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16 --trust-remote-code --dtype bfloat16 --video-pruning-rate 0
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16 --trust-remote-code --dtype bfloat16 --video-pruning-rate 0
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16 --trust-remote-code --dtype bfloat16 --video-pruning-rate 0
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16 --trust-remote-code --dtype bfloat16 --video-pruning-rate 0
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16 --trust-remote-code --dtype bfloat16 --video-pruning-rate 0
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16 --trust-remote-code --dtype bfloat16 --video-pruning-rate 0
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16 --trust-remote-code --dtype bfloat16 --video-pruning-rate 0
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16 --trust-remote-code --dtype bfloat16 --video-pruning-rate 0
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16 --trust-remote-code --dtype bfloat16 --video-pruning-rate 0
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16 --trust-remote-code --dtype bfloat16 --video-pruning-rate 0
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16 --trust-remote-code --dtype bfloat16 --video-pruning-rate 0
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16 --trust-remote-code --dtype bfloat16 --video-pruning-rate 0
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16 --trust-remote-code --dtype bfloat16 --video-pruning-rate 0
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16 --trust-remote-code --dtype bfloat16 --video-pruning-rate 0
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16 --trust-remote-code --dtype bfloat16 --video-pruning-rate 0
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16 --trust-remote-code --dtype bfloat16 --video-pruning-rate 0
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16 --trust-remote-code --dtype bfloat16 --video-pruning-rate 0
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16 --trust-remote-code --dtype bfloat16 --video-pruning-rate 0
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16 --trust-remote-code --dtype bfloat16 --video-pruning-rate 0
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16 --trust-remote-code --dtype bfloat16 --video-pruning-rate 0
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16 --trust-remote-code --dtype bfloat16 --video-pruning-rate 0
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16 --trust-remote-code --dtype bfloat16 --video-pruning-rate 0
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16 --trust-remote-code --dtype bfloat16 --video-pruning-rate 0
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16 --trust-remote-code --dtype bfloat16 --video-pruning-rate 0
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16 --trust-remote-code --dtype bfloat16 --video-pruning-rate 0
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16 --trust-remote-code --dtype bfloat16 --video-pruning-rate 0
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16 --trust-remote-code --dtype bfloat16 --video-pruning-rate 0
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16 --trust-remote-code --dtype bfloat16 --video-pruning-rate 0
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16 --trust-remote-code --dtype bfloat16 --video-pruning-rate 0
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16 --trust-remote-code --dtype bfloat16 --video-pruning-rate 0
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16 --trust-remote-code --dtype bfloat16 --video-pruning-rate 0
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16 --trust-remote-code --dtype bfloat16 --video-pruning-rate 0
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16 --trust-remote-code --dtype bfloat16 --video-pruning-rate 0
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16 --trust-remote-code --dtype bfloat16 --video-pruning-rate 0
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16 --trust-remote-code --dtype bfloat16 --video-pruning-rate 0
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16 --trust-remote-code --dtype bfloat16 --video-pruning-rate 0
Inference with SGLangbash
sglang serve --trust-remote-code --model-path nvidia/Nemotron-Nano-12B-v2-VL-BF16 --max-mamba-cache-size 256 # Adjust '--max-mamba-cache-size' as needed, to fit in memory
Inference with SGLangbash
sglang serve --trust-remote-code --model-path nvidia/Nemotron-Nano-12B-v2-VL-BF16 --max-mamba-cache-size 256 # Adjust '--max-mamba-cache-size' as needed, to fit in memory
Inference with SGLangbash
sglang serve --trust-remote-code --model-path nvidia/Nemotron-Nano-12B-v2-VL-BF16 --max-mamba-cache-size 256 # Adjust '--max-mamba-cache-size' as needed, to fit in memory
Inference with SGLangbash
sglang serve --trust-remote-code --model-path nvidia/Nemotron-Nano-12B-v2-VL-BF16 --max-mamba-cache-size 256 # Adjust '--max-mamba-cache-size' as needed, to fit in memory
Inference with SGLangbash
sglang serve --trust-remote-code --model-path nvidia/Nemotron-Nano-12B-v2-VL-BF16 --max-mamba-cache-size 256 # Adjust '--max-mamba-cache-size' as needed, to fit in memory
Inference with SGLangbash
sglang serve --trust-remote-code --model-path nvidia/Nemotron-Nano-12B-v2-VL-BF16 --max-mamba-cache-size 256 # Adjust '--max-mamba-cache-size' as needed, to fit in memory
Inference with SGLangbash
sglang serve --trust-remote-code --model-path nvidia/Nemotron-Nano-12B-v2-VL-BF16 --max-mamba-cache-size 256 # Adjust '--max-mamba-cache-size' as needed, to fit in memory
Inference with SGLangbash
sglang serve --trust-remote-code --model-path nvidia/Nemotron-Nano-12B-v2-VL-BF16 --max-mamba-cache-size 256 # Adjust '--max-mamba-cache-size' as needed, to fit in memory
Inference with SGLangbash
sglang serve --trust-remote-code --model-path nvidia/Nemotron-Nano-12B-v2-VL-BF16 --max-mamba-cache-size 256 # Adjust '--max-mamba-cache-size' as needed, to fit in memory
Inference with SGLangbash
sglang serve --trust-remote-code --model-path nvidia/Nemotron-Nano-12B-v2-VL-BF16 --max-mamba-cache-size 256 # Adjust '--max-mamba-cache-size' as needed, to fit in memory
Inference with SGLangbash
sglang serve --trust-remote-code --model-path nvidia/Nemotron-Nano-12B-v2-VL-BF16 --max-mamba-cache-size 256 # Adjust '--max-mamba-cache-size' as needed, to fit in memory
Inference with SGLangbash
sglang serve --trust-remote-code --model-path nvidia/Nemotron-Nano-12B-v2-VL-BF16 --max-mamba-cache-size 256 # Adjust '--max-mamba-cache-size' as needed, to fit in memory
Inference with SGLangbash
sglang serve --trust-remote-code --model-path nvidia/Nemotron-Nano-12B-v2-VL-BF16 --max-mamba-cache-size 256 # Adjust '--max-mamba-cache-size' as needed, to fit in memory
Inference with SGLangbash
sglang serve --trust-remote-code --model-path nvidia/Nemotron-Nano-12B-v2-VL-BF16 --max-mamba-cache-size 256 # Adjust '--max-mamba-cache-size' as needed, to fit in memory
Inference with SGLangbash
sglang serve --trust-remote-code --model-path nvidia/Nemotron-Nano-12B-v2-VL-BF16 --max-mamba-cache-size 256 # Adjust '--max-mamba-cache-size' as needed, to fit in memory
Inference with SGLangbash
sglang serve --trust-remote-code --model-path nvidia/Nemotron-Nano-12B-v2-VL-BF16 --max-mamba-cache-size 256 # Adjust '--max-mamba-cache-size' as needed, to fit in memory
Inference with SGLangbash
sglang serve --trust-remote-code --model-path nvidia/Nemotron-Nano-12B-v2-VL-BF16 --max-mamba-cache-size 256 # Adjust '--max-mamba-cache-size' as needed, to fit in memory
Inference with SGLangbash
sglang serve --trust-remote-code --model-path nvidia/Nemotron-Nano-12B-v2-VL-BF16 --max-mamba-cache-size 256 # Adjust '--max-mamba-cache-size' as needed, to fit in memory
Inference with SGLangbash
sglang serve --trust-remote-code --model-path nvidia/Nemotron-Nano-12B-v2-VL-BF16 --max-mamba-cache-size 256 # Adjust '--max-mamba-cache-size' as needed, to fit in memory
Inference with SGLangbash
sglang serve --trust-remote-code --model-path nvidia/Nemotron-Nano-12B-v2-VL-BF16 --max-mamba-cache-size 256 # Adjust '--max-mamba-cache-size' as needed, to fit in memory
Inference with SGLangbash
sglang serve --trust-remote-code --model-path nvidia/Nemotron-Nano-12B-v2-VL-BF16 --max-mamba-cache-size 256 # Adjust '--max-mamba-cache-size' as needed, to fit in memory
Inference with SGLangbash
sglang serve --trust-remote-code --model-path nvidia/Nemotron-Nano-12B-v2-VL-BF16 --max-mamba-cache-size 256 # Adjust '--max-mamba-cache-size' as needed, to fit in memory
Inference with SGLangbash
sglang serve --trust-remote-code --model-path nvidia/Nemotron-Nano-12B-v2-VL-BF16 --max-mamba-cache-size 256 # Adjust '--max-mamba-cache-size' as needed, to fit in memory
Inference with SGLangbash
sglang serve --trust-remote-code --model-path nvidia/Nemotron-Nano-12B-v2-VL-BF16 --max-mamba-cache-size 256 # Adjust '--max-mamba-cache-size' as needed, to fit in memory
Inference with SGLangbash
sglang serve --trust-remote-code --model-path nvidia/Nemotron-Nano-12B-v2-VL-BF16 --max-mamba-cache-size 256 # Adjust '--max-mamba-cache-size' as needed, to fit in memory
Inference with SGLangbash
sglang serve --trust-remote-code --model-path nvidia/Nemotron-Nano-12B-v2-VL-BF16 --max-mamba-cache-size 256 # Adjust '--max-mamba-cache-size' as needed, to fit in memory
Inference with SGLangbash
sglang serve --trust-remote-code --model-path nvidia/Nemotron-Nano-12B-v2-VL-BF16 --max-mamba-cache-size 256 # Adjust '--max-mamba-cache-size' as needed, to fit in memory
Inference with SGLangbash
sglang serve --trust-remote-code --model-path nvidia/Nemotron-Nano-12B-v2-VL-BF16 --max-mamba-cache-size 256 # Adjust '--max-mamba-cache-size' as needed, to fit in memory
Inference with SGLangbash
sglang serve --trust-remote-code --model-path nvidia/Nemotron-Nano-12B-v2-VL-BF16 --max-mamba-cache-size 256 # Adjust '--max-mamba-cache-size' as needed, to fit in memory
Inference with SGLangbash
sglang serve --trust-remote-code --model-path nvidia/Nemotron-Nano-12B-v2-VL-BF16 --max-mamba-cache-size 256 # Adjust '--max-mamba-cache-size' as needed, to fit in memory
Inference with SGLangbash
sglang serve --trust-remote-code --model-path nvidia/Nemotron-Nano-12B-v2-VL-BF16 --max-mamba-cache-size 256 # Adjust '--max-mamba-cache-size' as needed, to fit in memory
Inference with SGLangbash
sglang serve --trust-remote-code --model-path nvidia/Nemotron-Nano-12B-v2-VL-BF16 --max-mamba-cache-size 256 # Adjust '--max-mamba-cache-size' as needed, to fit in memory
Inference with SGLangbash
sglang serve --trust-remote-code --model-path nvidia/Nemotron-Nano-12B-v2-VL-BF16 --max-mamba-cache-size 256 # Adjust '--max-mamba-cache-size' as needed, to fit in memory
Inference with SGLangbash
sglang serve --trust-remote-code --model-path nvidia/Nemotron-Nano-12B-v2-VL-BF16 --max-mamba-cache-size 256 # Adjust '--max-mamba-cache-size' as needed, to fit in memory
Inference with SGLangbash
sglang serve --trust-remote-code --model-path nvidia/Nemotron-Nano-12B-v2-VL-BF16 --max-mamba-cache-size 256 # Adjust '--max-mamba-cache-size' as needed, to fit in memory
Inference with SGLangbash
sglang serve --trust-remote-code --model-path nvidia/Nemotron-Nano-12B-v2-VL-BF16 --max-mamba-cache-size 256 # Adjust '--max-mamba-cache-size' as needed, to fit in memory
Inference with SGLangbash
sglang serve --trust-remote-code --model-path nvidia/Nemotron-Nano-12B-v2-VL-BF16 --max-mamba-cache-size 256 # Adjust '--max-mamba-cache-size' as needed, to fit in memory
Inference with SGLangbash
sglang serve --trust-remote-code --model-path nvidia/Nemotron-Nano-12B-v2-VL-BF16 --max-mamba-cache-size 256 # Adjust '--max-mamba-cache-size' as needed, to fit in memory
Inference with SGLangbash
sglang serve --trust-remote-code --model-path nvidia/Nemotron-Nano-12B-v2-VL-BF16 --max-mamba-cache-size 256 # Adjust '--max-mamba-cache-size' as needed, to fit in memory
Inference with SGLangbash
sglang serve --trust-remote-code --model-path nvidia/Nemotron-Nano-12B-v2-VL-BF16 --max-mamba-cache-size 256 # Adjust '--max-mamba-cache-size' as needed, to fit in memory
Inference with SGLangbash
sglang serve --trust-remote-code --model-path nvidia/Nemotron-Nano-12B-v2-VL-BF16 --max-mamba-cache-size 256 # Adjust '--max-mamba-cache-size' as needed, to fit in memory

Deploy This Model

Production-ready deployment in minutes

Together.ai

Instant API access to this model

Fastest API

Production-ready inference API. Start free, scale to millions.

Try Free API

Replicate

One-click model deployment

Easiest Setup

Run models in the cloud with simple API. No DevOps required.

Deploy Now

Disclosure: We may earn a commission from these partners. This helps keep LLMYourWay free.