بازدان بۆ ناوەڕۆکی سەرەکی

NVIDIA · دەق

مۆدێلەکانی NVIDIA Nemotron: وەشانەکان، تایبەتمەندییەکان، پێداویستییەکانی GPU و میوانداری

NVIDIA Nemotron provides Ultra, Super, Nano, Omni and Lightning tiers optimized for different throughput and reasoning targets.

Technical deployment reference illustration for NVIDIA Nemotron
Reference deployment flow; exact architecture facts are listed separately.

پوختە و مێژوو

NVIDIA Nemotron is an official NVIDIA model family represented here through independently verified release, خاڵی وەشان, license, ژینگەی جێبەجێکردن and hardware evidence. NVIDIA Nemotron provides Ultra, Super, Nano, Omni and Lightning tiers optimized for different throughput and reasoning targets. Current public releases are grouped by the General, Omni, Speaker Diarization tracks so sibling sizes and specialist branches are not presented as false chronological generations.

FusionPointAI currently tracks 9 certified public NVIDIA Nemotron releases. The catalogue preserves release dates and evaluates Current, Recent, Previous and Legacy status within each model track rather than by database insertion order.

NVIDIA-optimized formats
Multiple scale tiers
Enterprise reasoning

تەلارسازی و مەودای مۆدێل

The verified public range spans 0.1B to 550B total parameters and context windows up to 262,144 تۆکنەکان. Each release states whether it is dense or mixture-of-experts and records active parameters separately when the official source publishes them.

وەشانە بڵاوکراوەکان9
ڕێڕەوەکانی مۆدێل3
نەوەی ئێستاNVIDIA Nemotron 3.5 Lightning 30B-A3B
دوا جار پشتڕاستکراوەتەوە2026-09-04T00:00:00.000000Z

نەوەکان، ڕێڕەوەکان و جۆرەکان

گشتی

ئۆمنی

ناسینەوەی قسەکەر

ژینگەی جێبەجێکردن

Choose a specific NVIDIA Nemotron release and certified خاڵی وەشان before sizing hardware. FusionPointAI rejects unknown ژینگەی جێبەجێکردن configurations, calculates resident memory from total model weights, then distinguishes globally compatible GPUs from currently rentable inventory.

Validate the exact خاڵی وەشان license, ژینگەی جێبەجێکردن version, precision kernel, context length, concurrency and multi-GPU topology. Active MoE parameters affect compute, but resident model memory continues to use total stored weights.

بەکارهێنانە باوەکان

High-throughput inference
Reasoning services
Multimodal agents

پوختەی مۆڵەت

Licenses are certified per release, not inferred from the provider. Review the release page before commercial deployment because terms can differ between generations and variants.

Commercial-use status is a source-backed catalogue classification, not legal advice. Follow the linked official license and attribution requirements.

ڕێڕەوی کاتیی وەشان

nvidia/nemotron/nvidia-nemotron-3-ultra-550b-a55b-nvfp4

وردەکاریی سەرچاوە

سەرچاوەی فەرمی

وەشانی سەرچاوە: abcfa162387e5fea3060af98d7675b438f84aa342c134f52ae47f79898af65c1

nvidia/nemotron/nvidia-nemotron-35-lightning-30b-a3b-nvfp4

وردەکاریی سەرچاوە

سەرچاوەی فەرمی

وەشانی سەرچاوە: f3923f78a1a7f78f04eb3b3b86306923df43dfa7f72f5989ab0aa4c2eb8c54ff

nvidia/nemotron/nvidia-nemotron-35-lightning-30b-a3b-nvfp4-dspark

وردەکاریی سەرچاوە

سەرچاوەی فەرمی

وەشانی سەرچاوە: b939d8a0adc9e4ab46fc50be6172409fca1a92a532e347d2274c153d5d538e26

nvidia/nemotron/nvidia-nemotron-35-lightning-30b-a3b-nvfp4-dflash

وردەکاریی سەرچاوە

سەرچاوەی فەرمی

وەشانی سەرچاوە: 7659a063e177eb2dbeac048c499e30fd10c5a7ced958405c505318957fa23562

nvidia/nemotron/nemotron-3-ultra-550b-a55b

وردەکاریی سەرچاوە

سەرچاوەی فەرمی

وەشانی سەرچاوە: ac6e67d70b7e8a6f10d1323aee594980c0fdb0a43eec104ffbe84e87897885ec

nvidia/nemotron/nemotron-3-5-lightning-30b-a3b

وردەکاریی سەرچاوە

سەرچاوەی فەرمی

وەشانی سەرچاوە: dc17dd660dd197ae989def582e149d930b898c480ac56fbc28aef4ad5508fb32

nvidia/nemotron/nemotron-3-diarization-preview

وردەکاریی سەرچاوە

سەرچاوەی فەرمی

وەشانی سەرچاوە: a43022e40b9883fb75078c47c5d4c995436863bb26e26f13a1a7e836ea519229

nvidia/nemotron/nemotron-3-super-120b-a12b

وردەکاریی سەرچاوە

سەرچاوەی فەرمی

وەشانی سەرچاوە: 680e0e5a3131d196ec831e0f1d320c7e0a5405faac89108daf9591babe14134c

nvidia/nemotron/nemotron-3-nano-omni-30b-a3b-reasoning-fp8

وردەکاریی سەرچاوە

سەرچاوەی فەرمی

وەشانی سەرچاوە: dd885e9548478d0d433c1239ed4598ad4a9faf7f58a8c706ab89885e5e2117fa

پرسیارە باوەکان

Which NVIDIA Nemotron release is current?

Current releases are NVIDIA Nemotron 3.5 Lightning 30B-A3B, NVIDIA Nemotron 3 Nano Omni 30B-A3B Reasoning FP8, evaluated within their respective tracks.

Can NVIDIA Nemotron be self-hosted?

Only releases with a verified official خاڵی وەشان and supported ژینگەی جێبەجێکردن configuration are presented as deployable.

Which GPU should run NVIDIA Nemotron?

GPU selection depends on the exact variant, خاڵی وەشان precision, context length and concurrency; use the release hardware recommendations rather than the family name alone.

سەرچاوە فەرمییەکان

دوا جار پشتڕاستکراوەتەوە: 2026-09-04