NVIDIA Nemotron · Omni · Nemotron 3 Nano Omni
NVIDIA Nemotron 3 Nano Omni 30B-A3B Reasoning FP8 is a current Omni release in the NVIDIA Nemotron family, certified from its immutable official source revision.
NVIDIA Nemotron 3 Nano Omni 30B-A3B Reasoning FP8 is an official self-hostable NVIDIA release in the NVIDIA Nemotron Omni track. It uses NemotronH_Nano_Omni_Reasoning_V3, carries 31B / 3B MoE, supports a verified context window of 262,144 tokens, and exposes only source-certified checkpoints and runtime combinations. Its release, license and deployment facts are tied to the official repository revision rather than inferred from the family name.
NVIDIA Nemotron 3 Nano Omni 30B-A3B Reasoning FP8 uses NemotronH_Nano_Omni_Reasoning_V3 with 31B / 3B MoE. The stored architecture profile records 64 layers, hidden width 8192, 64 attention heads and a 262,144 token context ceiling where the official configuration publishes those fields.
Only exact, source-certified variants attached to this release are shown.
nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-FP8
Official · FP8 · safetensors
Runtime certified: vLLM SGLang TensorRT-LLM Llama.cpp
| Precision / quantization | Format | Bits | Publisher trust | Deployment state |
|---|---|---|---|---|
| FP8 | safetensors | 8 | Official | Runtime certified |
Use only the listed vllm, sglang, tensorrt-llm, llama.cpp runtime configuration with the exact checkpoint precision. The recommendation engine checks weight memory, KV cache, runtime overhead, safety headroom, GPU architecture and topology before ranking rentable and reference hardware.
Recommended best value
141 GB total VRAM · nvswitch
90.17 GB headroom · Limited capacity
USD 2,345 / monthLowest-cost viable
72 GB total VRAM · pcie
21.17 GB headroom · Available
USD 750 / monthHighest performance
141 GB total VRAM · nvswitch
90.17 GB headroom · Limited capacity
USD 2,345 / monthThe full 31B resident weight set must fit across the selected GPUs. Context and concurrency add KV-cache memory; MoE active parameters do not replace resident-weight memory.
NVIDIA Nemotron 3 Nano Omni 30B-A3B Reasoning FP8 is published under NVIDIA Open Model Agreement. The release-scoped official license link and verification date are retained with the catalogue record.
Commercial Use Allowed With Conditions. Commercial use is conditional. Review the linked official terms before deployment.
Source revision: dd885e9548478d0d433c1239ed4598ad4a9faf7f58a8c706ab89885e5e2117fa
The exact estimate depends on checkpoint precision, context and concurrency; the page recommendation uses the certified memory engine and compatible runtime configurations.
Certified upstream runtime evidence is available for vllm, sglang, tensorrt-llm, llama.cpp.
The stored commercial classification is Commercial Use Allowed With Conditions. Consult the official NVIDIA Open Model Agreement terms for the final obligations.
Last verified: 2026-08-26
