NVIDIA

Nemotron Cascade 2 30B A3B

Tool callingReasoning

Nemotron model for efficient reasoning, coding, and specialized AI agents

Context
256K
Released
6mo ago
Parameters
30B

Sources:models.dev

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
March 24, 2026
Model ID
nvidia/nemotron-cascade-2-30b-a3b
Openness
Open weights
License
—
Parameters
30B
Input modalities
text
Output modalities
text
Modality
text->text
Max output tokens
33K
Hugging Face
—
Source freshness
Metadata synced Oct 8, 2026, 10:17 PM UTC
Additional source evidence
Source model
nvidia/nemotron-cascade-2-30b-a3b
Source family
nemotron
Last updated
2026-04-09
Model context
256K
Model output limit
33K
Open weights
Yes
File attachments
No
Reasoning
Yes
Tool calling
Yes
Temperature control
Yes
Complete source record (JSON)
{
  "id": "nvidia/nemotron-cascade-2-30b-a3b",
  "name": "Nemotron Cascade 2 30B A3B",
  "description": "Nemotron model for efficient reasoning, coding, and specialized AI agents",
  "family": "nemotron",
  "last_updated": "2026-04-09",
  "attachment": false,
  "reasoning": true,
  "tool_call": true,
  "temperature": true,
  "modalities": {
    "input": [
      "text"
    ],
    "output": [
      "text"
    ]
  },
  "limit": {
    "context": 256000,
    "output": 32768
  },
  "release_date": "2026-03-24",
  "open_weights": true
}

Infrastructure

Provider availability

All providers
Provider endpoint data will appear after this model's first OpenRouter endpoint sync.

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