NVIDIA-Nemotron-Nano-12B-v2

17.9K
132
131K
Long context
12.0B
6 languages
—
by
nvidia
Language Model
OTHER
12B params
Fair
18K downloads
Community-tested
Try on Hugging FaceAdd to Compare
Edge AI:
Mobile
Laptop
Server
27GB+ RAM
Mobile
Laptop
Server
Quick Summary

--- license: other license_name: nvidia-open-model-license license_link: >- https://www.

Device Compatibility

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

Code Examples

**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
**Use it with vLLM**bashvllm
pip install -U "vllm>=0.10.1"
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32
bashvllm
vllm serve nvidia/NVIDIA-Nemotron-Nano-12B-v2 \
    --trust-remote-code \
    --max-num-seqs 64 \
    --mamba_ssm_cache_dtype float32

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.