Any-to-Any
Transformers
Safetensors
English
NemotronH_Nano_Omni_Reasoning_V3
feature-extraction
4-bit precision
aarch64
abliterated
aeon
aeon-7
agentic
arm64
audio
blackwell
chat
chunked-prefill
coding
conversational
dgx-spark
english
flashinfer-cutlass
fp4
fp8-kv-cache
function-calling
gb10
gpu
grace-blackwell
hybrid
hybrid-attention
instruct
long-context
mamba
mamba2
modelopt
Mixture of Experts
multimodal
native-fp4
nemotron
nemotron-h
nvfp4
nvidia
openai-api
openai-compatible
parakeet
prefix-caching
production-ready
quantization
quantized
radio
reasoning
refusal-removed
sm_121a
thinking
tool-calling
uncensored
unfiltered
vision
vision-language
vllm
weight-quantization
custom_code
8-bit precision
Ctrl+K