Nemotron 3 Nano 30B A3B
Nemotron 3 Nano 30B A3BRankingin non-thinking mode?
Alternatives?
CheaperGPT OSS 120BunstatedOpensame-43%$0.03 / $0.15Memory (4-bit): 19 GB → 70 GBBetterGPT-6 Lunamaxwins 52%+90%$0.068Function calling only with none · Chat Completions+3
OpenGemma 4 31Bunstatedwins 60%+52%$0.10 / $0.34CheaperGemma 3 12BunstatedOpenwins 46%-40%$0.05 / $0.10
CheaperGranite 4.2 3BunstatedOpenwins 42%-50%$0.03 / $0.12Context: 131K → 128KGPT OSS 120BunstatedOpensame-43%$0.03 / $0.15Memory (4-bit): 19 GB → 70 GBGemma 3 12BunstatedOpenwins 46%-40%$0.05 / $0.10Granite 4.2 3BunstatedOpenwins 42%-50%$0.03 / $0.12Context: 131K → 128KGPT-6 Lunamaxwins 52%+90%$0.068Function calling only with none · Chat Completions+3
Claude Haiku 5.5highwins 55%+90%$0.079Remove sampling parameters+5GPT-5.6 Lunaxhighwins 59%+329%$0.085GPT-5.6 Terraxhighwins 60%+4,186%$0.63Prompts with >272K input tokensGPT-6.1 Solmaxwins 60%+3,710%$0.72Remove unsupported parameters+5Gemma 4 31BunstatedOpenwins 60%+52%$0.10 / $0.34
Qwen3.8 27BunstatedOpenwins 60%+811%$0.42 / $2.55max_tokens range · QwenCloud+4Gemma 4 26B A4BunstatedOpenwins 59%+150%$0.15 / $0.60Qwen 3.5 27BunstatedOpenwins 57%+686%$0.30 / $2.40Qwen 3.5 35B A3BunstatedOpenwins 54%+555%$0.25 / $2Memory (4-bit): 19 GB → 22 GBNVIDIA Nemotron 3 Ultra 550B A55B NVFP4Openwins 61%——Memory (4-bit): 19 GB → 182 GBNVIDIA Nemotron 3.5 Super VL 120B A12B NVFP4Openwins 57%—$0.08 / $0.45Memory (4-bit): not verifiedNVIDIA Nemotron 3.5 Lightning 30B A3B NVFP4Opensame——Llama Nemotron Super 49B v1.5unstatedOpenwins 47%—$0.40 / $0.40Context: 131K → 128K+1Llama 3 3 Nemotron Super 49B v1Openwins 47%——Memory (4-bit): 19 GB → 30 GB+1Llama 3.1 Nemotron 70B InstructOpenwins 41%—$1.20 / $1.20Memory (4-bit): not verifiedNemotron 4 340B InstructOpenwins 31%—$4.20 / $4.20Context: 131K → 4K+1NVIDIA Nemotron Labs Dory 1.0 4BOpenn/a——All NVIDIA models →Run it yourself
estimateBenchmarks
all categoriesFAQ
How much does Nemotron 3 Nano 30B A3B cost?›
$0.06 per 1M input tokens and $0.24 per 1M output tokens (cheapest host: OpenRouter).
Is Nemotron 3 Nano 30B A3B free to use?›
Yes, there is a free API option.
How good is Nemotron 3 Nano 30B A3B, and what is it best at?›
#290 of 336 in Chat & Knowledge, #77 of 134 in Coding, #112 of 135 in Agents & Tool Use, #143 of 197 in Writing & Language, #121 of 135 in Vision & Documents.
Is Nemotron 3 Nano 30B A3B better than Mercury 2?›
On Arena Text · English, Nemotron 3 Nano 30B A3B scores 1,377.6 vs 1,378.3 — about the same.
How can I use Nemotron 3 Nano 30B A3B?›
Through the API of DeepInfra, Nebius, Novita.
What is the context window of Nemotron 3 Nano 30B A3B?›
131K tokens, with up to 131K output tokens.
When was Nemotron 3 Nano 30B A3B released? Is there a newer version?›
Released 2025-12-04. It is the current version in its line.
Is Nemotron 3 Nano 30B A3B open source?›
Yes, the weights are open (nvidia-nemotron-open-model-license licence).
Can I run Nemotron 3 Nano 30B A3B locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can Nemotron 3 Nano 30B A3B read images?›
No, it accepts text only.
What is Nemotron 3 Nano 30B A3B?›
Nemotron 3 Nano 30B A3B is an open-weights language model from NVIDIA, released Dec 2025.
What are the best alternatives to Nemotron 3 Nano 30B A3B?›
GPT OSS 120B (cheaper), GPT-6 Luna (better), Gemma 4 31B (open weights).