Nemotron 3 Nano 30B A3B

Tool callingStructured outputReasoning

Hugging Face Launch post Website

Small Nemotron 3 MoE for efficient coding, math, and long-context agents

Context: 262K
Released: 10mo ago
Parameters: 30B
Input / 1M tokens: $0.06
Output / 1M tokens: $0.24

Sources:models.devOpenRouter

Benchmarks

DeepSWE is the primary coding benchmark where an exact model evaluation exists. Other sourced evaluations appear below; missing scores are not zero.

Not evaluated in DeepSWE 1.1 as of 2026-09-22. Results are only shown for exact model versions in the official dataset. Official leaderboard.

No benchmark results have been matched to this model yet.

Specifications

Developer: NVIDIA
Model family: Nemotron
Type: Language model
Predecessor: —
Successor: —
Released: December 15, 2025
Model ID: nvidia/nemotron-3-nano-30b-a3b
Openness: Open weights
License: —
Parameters: 30B
Input modalities: text
Output modalities: text
Modality: text->text
Native context: 1M
Tokenizer: Other
Max output tokens: 236K
Hugging Face: nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
Source freshness: Metadata synced Oct 8, 2026, 10:17 PM UTC

Open-weight builds

Ollama variants

Every published Ollama tag matched to this model, including parameter editions, instruction/base variants, and quantized builds.

7 builds

Variant	Parameters	Type	Quantization	Size	Context	Input
nemotron-3-nano:4b-bf16	4B	—	BF16	8 GB	256K	text
nemotron-3-nano:4b-q8_0	4B	—	Q8_0	4.2 GB	256K	text
nemotron-3-nano:4b	4B	—	—	2.8 GB	256K	text
nemotron-3-nano:30b-cloud	30B	cloud	—	—	1M	text
nemotron-3-nano:30b-a3b-fp16	30B	—	FP16	63 GB	1M	text
nemotron-3-nano:latest	30B	—	Q4_K_M	24 GB	1M	text
nemotron-3-nano:30b-a3b-q8_0	30B	—	Q8_0	34 GB	1M	text

Additional source evidence

Source model: nvidia/nemotron-3-nano-30b-a3b
Source family: nemotron
Last updated: 2025-12-15
Model context: 262K
Model output limit: 262K
Open weights: Yes
File attachments: No
Reasoning: Yes
Tool calling: Yes
Temperature control: Yes

Complete source record (JSON)

{
  "id": "nvidia/nemotron-3-nano-30b-a3b",
  "name": "Nemotron 3 Nano 30B A3B",
  "description": "Small Nemotron 3 MoE for efficient coding, math, and long-context agents",
  "family": "nemotron",
  "last_updated": "2025-12-15",
  "attachment": false,
  "reasoning": true,
  "tool_call": true,
  "temperature": true,
  "modalities": {
    "input": [
      "text"
    ],
    "output": [
      "text"
    ]
  },
  "limit": {
    "context": 262144,
    "output": 262144
  },
  "release_date": "2025-12-15",
  "open_weights": true
}

Infrastructure

Provider availability

All providers

Provider	Endpoint	Context	Input /M tokens	Output /M tokens	Cached input /M tokens	Cache write /M tokens	Uptime 1d	Data handling
Novita	novita/fp4	262K	$0.05	$0.20	—	—	100.00%	ZDR: Yes Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15
Nebius	nebius/fp8	262K	$0.06	$0.24	—	—	97.09%	ZDR: Yes Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15

Provider data:OpenRouter

Deployment graph

Can I run this?

Vertical Tabs only shows compatibility when it has structured evidence tying this exact model to hardware, runtime, quantization, memory use, and observed performance.

Browse hardware